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

    Neuronpedia

    INDEX
    Explanations

    terms used in sports and organized events

    oai_token-act-pair · gemini-2.0-flash

    gendered entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.86
    elemField
    -0.68
     مشين
    -0.63
     createSlice
    -0.59
    ValueStyle
    -0.56
    styleType
    -0.56
    TypedDataSet
    -0.54
    anthene
    -0.54
    RegistryLite
    -0.53
    tvguidetime
    -0.53
    POSITIVE LOGITS
    __*/
    0.65
     mens
    0.64
    mens
    0.59
     solde
    0.59
    ADT
    0.59
    ########.
    0.57
     mixte
    0.57
     general
    0.56
     общий
    0.56
    unisex
    0.55
    Act Density 1.254%

    No Known Activations