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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hemen
    -0.08
     Mannheim
    -0.08
    .Zoom
    -0.07
     empresário
    -0.07
     ICS
    -0.07
    党员
    -0.07
    ockey
    -0.07
     YYST
    -0.07
     empresários
    -0.07
    ICOS
    -0.07
    POSITIVE LOGITS
     redemption
    0.10
     humanity
    0.10
    ，实现
    0.09
     someday
    0.09
     rumored
    0.09
     cures
    0.09
     rogue
    0.08
     revenge
    0.08
     forgotten
    0.08
     dreams
    0.08
    Act Density 0.050%

    No Known Activations