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

    Neuronpedia

    INDEX
    Explanations

    Math/series expansions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elerine
    -0.06
    σμ
    -0.06
    ¨
    -0.06
     ="";↵
    -0.06
    尘
    -0.06
     Wine
    -0.06
     homophobic
    -0.06
    $total
    -0.06
    ilerin
    -0.06
     Phaser
    -0.06
    POSITIVE LOGITS
     uncompressed
    0.07
    fts
    0.07
    .faces
    0.06
    ไ
    0.06
     replen
    0.06
    non
    0.06
     inheritance
    0.06
     subsequ
    0.06
    _MP
    0.06
    frau
    0.06
    Act Density 0.026%

    No Known Activations