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

    Neuronpedia

    INDEX
    Explanations

    surrounding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kitty
    -0.08
     Clone
    -0.07
     Daily
    -0.07
     чолов
    -0.06
     troublesome
    -0.06
    _DEST
    -0.06
    CT
    -0.06
     محافظ
    -0.06
    Detroit
    -0.06
     parchment
    -0.06
    POSITIVE LOGITS
    Angle
    0.07
    '][
    0.06
    recent
    0.06
    ự
    0.06
    scopes
    0.06
    .last
    0.06
     nel
    0.06
    _native
    0.06
    Observ
    0.06
    (labels
    0.06
    Act Density 0.050%

    No Known Activations