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

    Neuronpedia

    INDEX
    Explanations

    Reinvesting dividends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _initialize
    -0.07
     Highlight
    -0.07
     Sketch
    -0.07
     Illustr
    -0.07
     advoc
    -0.07
     aplik
    -0.07
    /title
    -0.07
     released
    -0.07
     legs
    -0.07
     approves
    -0.07
    POSITIVE LOGITS
    冷
    0.07
    いろ
    0.07
    ग
    0.07
    응
    0.07
    בול
    0.07
    róż
    0.07
    -non
    0.07
    TLS
    0.06
     gg
    0.06
    curve
    0.06
    Act Density 0.025%

    No Known Activations