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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _race
    -0.08
     �
    -0.07
     Encoding
    -0.07
     dt
    -0.06
     березня
    -0.06
    總
    -0.06
    …"
    -0.06
    核心
    -0.06
    orrent
    -0.06
    нього
    -0.06
    POSITIVE LOGITS
     contained
    0.07
     अपर
    0.07
    AND
    0.07
     дела
    0.06
    .Tensor
    0.06
     Networks
    0.06
     CART
    0.06
     fertile
    0.06
     fined
    0.06
     stacking
    0.06
    Act Density 0.039%

    No Known Activations