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

    Neuronpedia

    INDEX
    Explanations

    instances of date and time information

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

    user or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.58
     >=",
    -0.52
     ModelExpression
    -0.48
    RegressionTest
    -0.48
     giudi
    -0.47
    ftagPool
    -0.45
    SharedDtor
    -0.45
    ：“……”
    -0.42
    kusen
    -0.41
    ագրություններ
    -0.40
    POSITIVE LOGITS
     PhpStorm
    0.79
     resourceCulture
    0.48
    UnitTesting
    0.46
    enumi
    0.44
    contentLoaded
    0.43
    expandindo
    0.41
    fjspx
    0.40
     invokingState
    0.40
    OGND
    0.39
    enumii
    0.39
    Act Density 0.001%

    No Known Activations