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

    Neuronpedia

    INDEX
    Explanations

    sub

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entes
    -0.06
     Pedido
    -0.06
    (holder
    -0.06
     Ils
    -0.06
    on
    -0.06
     Sister
    -0.06
    wald
    -0.06
     contracts
    -0.06
    (".",
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    :f
    0.07
     cinematic
    0.07
     fearless
    0.06
    FETCH
    0.06
    xCB
    0.06
    _Column
    0.06
    มห
    0.06
    USART
    0.06
    roring
    0.06
    ��
    0.06
    Act Density 0.010%

    No Known Activations