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

    Neuronpedia

    INDEX
    Explanations

    vertical line character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .GetName
    -0.07
     Trot
    -0.06
    [Byte
    -0.06
    éments
    -0.06
     IUser
    -0.06
    .getType
    -0.06
     minorities
    -0.06
     nama
    -0.06
    薮
    -0.06
    墘
    -0.06
    POSITIVE LOGITS
    placement
    0.08
    _of
    0.08
    🎠
    0.07
     geen
    0.07
    schließen
    0.07
    ;z
    0.07
     aantal
    0.07
     regulate
    0.07
     manipulated
    0.07
    不再
    0.06
    Act Density 0.004%

    No Known Activations