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

    Neuronpedia

    INDEX
    Explanations

    Information Technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (serial
    -0.07
    잖
    -0.07
     off
    -0.07
     Mondays
    -0.06
     combine
    -0.06
     всегда
    -0.06
    氣
    -0.06
    sqlite
    -0.06
    しています
    -0.06
     завжди
    -0.06
    POSITIVE LOGITS
    rror
    0.06
    esel
    0.06
    spar
    0.06
     filmm
    0.06
    abor
    0.06
     بان
    0.06
     Jihad
    0.06
     Rin
    0.06
    _reply
    0.06
    _execution
    0.05
    Act Density 0.152%

    No Known Activations