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

    Neuronpedia

    INDEX
    Explanations

    Noisy texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $_
    -0.07
    <option
    -0.07
    )e
    -0.06
    ');
↵
    -0.06
    -Qaeda
    -0.06
    ビ
    -0.06
    $arity
    -0.06
    渡
    -0.06
    Labour
    -0.06
    ()}
    -0.06
    POSITIVE LOGITS
    _ENDPOINT
    0.06
    623
    0.06
    过来
    0.06
     Useful
    0.06
    دو
    0.06
     attendant
    0.06
     Supported
    0.06
     Destination
    0.06
    ovich
    0.06
    ляв
    0.06
    Act Density 0.000%

    No Known Activations