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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    热爱
    -0.08
    幸福感
    -0.07
    青年
    -0.07
    Professor
    -0.07
    joy
    -0.07
     snap
    -0.07
    declare
    -0.07
    hog
    -0.07
     NJ
    -0.07
    mnop
    -0.07
    POSITIVE LOGITS
    Salt
    0.08
     kes
    0.07
    ⁻
    0.07
    ТЕ
    0.07
    ongan
    0.06
     slated
    0.06
    Songs
    0.06
     (_.
    0.06
    שיו
    0.06
    <X
    0.06
    Act Density 0.065%

    No Known Activations