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

    Neuronpedia

    INDEX
    Explanations

    ative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubi
    -0.07
    .URI
    -0.06
    _loss
    -0.06
     Hats
    -0.06
     зим
    -0.06
     derog
    -0.06
     bor
    -0.06
    ーロ
    -0.06
     Ham
    -0.06
     choses
    -0.06
    POSITIVE LOGITS
    vrd
    0.07
     ».
    0.06
    637
    0.06
    _FONT
    0.06
    ="--
    0.06
    ahoma
    0.06
    223
    0.06
     searchData
    0.06
    nums
    0.06
    (sd
    0.06
    Act Density 0.000%

    No Known Activations