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

    Neuronpedia

    INDEX
    Explanations

    multiplication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сты
    -0.07
    $args
    -0.06
     Child
    -0.06
     заказ
    -0.06
     Чем
    -0.06
     triples
    -0.06
    [cnt
    -0.06
     Johnny
    -0.06
     Encyclopedia
    -0.05
    ”↵↵
    -0.05
    POSITIVE LOGITS
    -held
    0.07
     περ
    0.07
    alte
    0.07
    �
    0.07
    easy
    0.07
    interpreted
    0.07
    äft
    0.06
    -rich
    0.06
    _TEXT
    0.06
    sson
    0.06
    Act Density 0.142%

    No Known Activations