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

    Neuronpedia

    INDEX
    Explanations

    comma-separated lists of items or information

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

    Followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UseVisualStyle
    -0.56
     lập
    -0.53
    OfBirth
    -0.52
    UnknownFields
    -0.52
     Hagen
    -0.51
    ogna
    -0.51
    WriteTagHelper
    -0.50
     form
    -0.49
     moment
    -0.48
    isel
    -0.48
    POSITIVE LOGITS
     препратки
    0.66
    новниш
    0.64
    таратура
    0.62
     '\\;'
    0.60
     bezeichneter
    0.59
     recevez
    0.59
    Nazionale
    0.57
    Personendaten
    0.56
     محفوظة
    0.54
     Italijani
    0.53
    Act Density 0.331%

    No Known Activations