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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ается
    -0.07
    aepernick
    -0.06
     humiliating
    -0.06
    Ni
    -0.06
    _album
    -0.06
    광
    -0.06
    erv
    -0.06
     whistleblower
    -0.06
     goal
    -0.06
     LIABILITY
    -0.06
    POSITIVE LOGITS
    .ribbon
    0.07
    の中
    0.06
    ा-
    0.06
    押
    0.06
    .appendTo
    0.06
     دسته
    0.06
    Earth
    0.06
    (pool
    0.06
     한
    0.06
     orthogonal
    0.06
    Act Density 0.038%

    No Known Activations