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

    Neuronpedia

    INDEX
    Explanations

    time spans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Base
    -0.06
     ноя
    -0.06
    locking
    -0.06
    Processing
    -0.06
     Scale
    -0.06
     Temper
    -0.06
     fractured
    -0.06
    GRID
    -0.06
     Παρα
    -0.06
    .Sequence
    -0.06
    POSITIVE LOGITS
     zel
    0.07
     Gill
    0.06
     singer
    0.06
    _bel
    0.06
    =v
    0.06
    )를
    0.06
    ULL
    0.06
     дела
    0.06
     Maher
    0.06
    xe
    0.06
    Act Density 0.020%

    No Known Activations