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

    Neuronpedia

    INDEX
    Explanations

    articles and prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    雯
    -0.07
    配方
    -0.07
     Dy
    -0.06
    .ht
    -0.06
    _foreign
    -0.06
     rencontr
    -0.06
     Derne
    -0.06
    SEN
    -0.06
    תצ
    -0.06
     Dialogue
    -0.06
    POSITIVE LOGITS
    устройств
    0.07
    新冠疫情
    0.07
     Defaults
    0.07
    RIPT
    0.07
    .cfg
    0.07
     endings
    0.07
    longitude
    0.07
    enção
    0.07
    STD
    0.06
     stringValue
    0.06
    Act Density 0.404%

    No Known Activations