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

    Neuronpedia

    INDEX
    Explanations

    Conversational writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    duce
    -0.07
     *)(
    -0.07
     EventEmitter
    -0.07
     interior
    -0.06
    .deepEqual
    -0.06
    uale
    -0.06
     مشاه
    -0.06
    ์โ
    -0.06
     gore
    -0.06
    _ti
    -0.06
    POSITIVE LOGITS
     Berry
    0.06
    Berry
    0.06
     Bud
    0.06
    ificent
    0.06
    PU
    0.06
     três
    0.06
     D
    0.06
     گزارش
    0.06
     blond
    0.05
     Shepard
    0.05
    Act Density 0.000%

    No Known Activations