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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _last
    -0.06
    يه
    -0.06
    Các
    -0.06
    ولي
    -0.06
     vampires
    -0.06
    ِه
    -0.06
     ruler
    -0.06
    亲
    -0.06
     изменения
    -0.06
    غط
    -0.06
    POSITIVE LOGITS
     hearts
    0.07
     δο
    0.07
    omes
    0.06
    ５
    0.06
    inating
    0.06
     os
    0.06
     nanop
    0.06
     resembling
    0.06
    atsu
    0.06
     Cindy
    0.06
    Act Density 0.134%

    No Known Activations