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

    Neuronpedia

    INDEX
    Explanations

    backslash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sony
    -0.07
     ("/
    -0.06
    [class
    -0.06
    continuous
    -0.06
     dom
    -0.06
    рабат
    -0.06
     '-',
    -0.06
    :ss
    -0.06
     SX
    -0.06
     Chevrolet
    -0.06
    POSITIVE LOGITS
    )*/↵
    0.07
    .previous
    0.07
    .By
    0.06
    UNDER
    0.06
     квіт
    0.06
     recruiters
    0.06
    ova
    0.06
    vasion
    0.06
    _MOVE
    0.06
     buurt
    0.06
    Act Density 0.012%

    No Known Activations