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

    Neuronpedia

    INDEX
    Explanations

    qualifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arrera
    -0.07
    owell
    -0.07
    urgence
    -0.07
    ��
    -0.06
     Polar
    -0.06
     Spit
    -0.06
     Aster
    -0.06
    사회
    -0.06
     trắng
    -0.06
    ेहर
    -0.06
    POSITIVE LOGITS
     individuals
    0.08
     cé
    0.07
     sost
    0.07
     dokument
    0.07
     estudio
    0.07
    .addItem
    0.07
     Potential
    0.06
    .M
    0.06
    .gms
    0.06
    .execute
    0.06
    Act Density 0.006%

    No Known Activations