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

    Neuronpedia

    INDEX
    Explanations

    expressions related to quantity and numerics

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

    words like Grandmother

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.57
     विश्वसनीयता
    -0.43
    ">//
    -0.41
    省市镇
    -0.40
    hisattva
    -0.40
    HomeAsUpEnabled
    -0.38
     Chwiliwch
    -0.37
    mutlich
    -0.36
    ultati
    -0.36
    RegressionTest
    -0.35
    POSITIVE LOGITS
    postsleuth
    0.54
     Италијани
    0.54
    XmlAccessType
    0.49
    ArgsConstructor
    0.48
     PyLong
    0.45
     BOR
    0.44
     ProtoMessage
    0.44
    UrlResolution
    0.42
     FLUID
    0.40
    isShowing
    0.40
    Act Density 0.508%

    No Known Activations