Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code-related constructs, particularly focusing on object-oriented programming principles and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    a later time

    np_acts-logits-general · gemini-2.0-flash

    purpose or subsequent action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.63
     addirittura
    -0.62
     propOrder
    -0.62
     themſelves
    -0.60
     persino
    -0.59
     itſelf
    -0.59
     AssemblyCompany
    -0.58
     unknownFields
    -0.56
    IsMutable
    -0.56
    unknownFields
    -0.54
    POSITIVE LOGITS
     subsequent
    0.79
     later
    0.75
     nanti
    0.73
     nantinya
    0.70
     Subsequent
    0.69
     purposes
    0.66
     später
    0.63
    later
    0.63
    後で
    0.61
     when
    0.60
    Act Density 0.757%

    No Known Activations