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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ext
    -0.08
    .notNull
    -0.06
    byter
    -0.06
    lásil
    -0.06
    stant
    -0.06
    zt
    -0.06
    _Part
    -0.06
    _pipe
    -0.06
    θήκη
    -0.06
    _Options
    -0.06
    POSITIVE LOGITS
     ingest
    0.07
     hilarious
    0.06
     Kub
    0.06
     Modular
    0.06
     国家
    0.06
     Dig
    0.06
     PAGE
    0.06
     Lov
    0.06
    shaled
    0.06
    藥
    0.06
    Act Density 0.015%

    No Known Activations