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

    Neuronpedia

    INDEX
    Explanations

    general statements/anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    httphttps
    -0.98
    RuleContext
    -0.88
    TagMode
    -0.75
     nakalista
    -0.69
    +#+
    -0.68
     Signalez
    -0.66
    ScopeManager
    -0.65
    ValueStyle
    -0.65
     kasarigan
    -0.63
    enumii
    -0.63
    POSITIVE LOGITS
    ruvate
    0.46
     otherwise
    0.46
     needs
    0.45
    ати
    0.44
    uwen
    0.43
    员
    0.43
    splat
    0.43
     GMAT
    0.42
    ORAGE
    0.41
    Chron
    0.41
    Act Density 0.002%

    No Known Activations