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

    Neuronpedia

    INDEX
    Explanations

    Chat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    111
    -0.06
    _train
    -0.06
     roy
    -0.06
    redirectTo
    -0.06
    _grid
    -0.06
    .getInputStream
    -0.06
     mornings
    -0.06
    324
    -0.06
    GT
    -0.06
     jade
    -0.06
    POSITIVE LOGITS
    }/${
    0.07
    ],
    0.07
     isr
    0.07
    igits
    0.07
    はない
    0.07
    aşa
    0.06
    ："
    0.06
     %[
    0.06
    など
    0.06
    扫
    0.06
    Act Density 0.009%

    No Known Activations