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

    Neuronpedia

    INDEX
    Explanations

    art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lazy
    -0.07
    .Fl
    -0.07
     earth
    -0.06
    .master
    -0.06
    _sum
    -0.06
    にある
    -0.06
    lém
    -0.06
     Humanity
    -0.06
    blers
    -0.06
    _slug
    -0.06
    POSITIVE LOGITS
     bipolar
    0.06
     attn
    0.06
     Maurice
    0.06
     hypoc
    0.06
    YSTICK
    0.06
    Purpose
    0.06
     Harvest
    0.06
    筑
    0.06
     archival
    0.06
    ji
    0.06
    Act Density 0.000%

    No Known Activations