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

    Neuronpedia

    INDEX
    Explanations

    mentions of programming language constructs and data structures

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

    figures or tables

    np_acts-logits-general · gemini-2.0-flash

    protocol buffer types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    جستارهای
    -0.58
     piú
    -0.53
    **,
    -0.52
    iedz
    -0.51
     %,
    -0.50
    ––
    -0.50
    ​,
    -0.50
     scelte
    -0.48
    windowFixed
    -0.47
     segreto
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    1.02
    tagHelperRunner
    0.82
    PyExc
    0.74
    tagHelper
    0.70
     resourceCulture
    0.68
     متعلقه
    0.68
    enumi
    0.67
    afficheront
    0.65
    protoimpl
    0.64
    principalTable
    0.63
    Act Density 0.040%

    No Known Activations