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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distinguished
    -0.07
    ез
    -0.07
     Genius
    -0.07
    (rel
    -0.07
     của
    -0.07
     invitation
    -0.07
     Doctors
    -0.07
    文科
    -0.07
    𬮱
    -0.07
    den
    -0.07
    POSITIVE LOGITS
     party
    0.07
    范冰
    0.07
    устрой
    0.07
     zwyk
    0.07
    oley
    0.07
    FontOfSize
    0.07
    arie
    0.07
    メーカ
    0.07
     תוכ
    0.07
    >";
    0.07
    Act Density 0.003%

    No Known Activations