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

    Neuronpedia

    INDEX
    Explanations

    numerical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curves
    -0.08
     correlations
    -0.08
     coag
    -0.08
    晶
    -0.08
    陈
    -0.07
     amic
    -0.07
    .nick
    -0.07
    เด
    -0.07
     acom
    -0.07
     curve
    -0.07
    POSITIVE LOGITS
     vliegen
    0.08
     бороть
    0.08
     ફ્લ
    0.08
     prüfen
    0.08
     Timber
    0.08
    izan
    0.08
     prosent
    0.08
     mail
    0.08
     usan
    0.07
    _activate
    0.07
    Act Density 0.007%

    No Known Activations