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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ِّ
    -0.07
    ِّ
    -0.07
     FIFA
    -0.06
    .matcher
    -0.06
     minded
    -0.06
     чор
    -0.06
    PLIED
    -0.06
    ActionTypes
    -0.06
    iddled
    -0.06
     mau
    -0.06
    POSITIVE LOGITS
     Holder
    0.06
    (bundle
    0.06
     fatigue
    0.06
    som
    0.06
    ford
    0.06
     erk
    0.06
     Garlic
    0.06
     uch
    0.06
    _dyn
    0.06
     especial
    0.06
    Act Density 0.002%

    No Known Activations