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

    Neuronpedia

    INDEX
    Explanations

    logarithmic equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rosie
    -0.09
    λών
    -0.08
    Kyle
    -0.08
     Lia
    -0.08
     stagger
    -0.08
     versos
    -0.08
    Executor
    -0.08
     Cathy
    -0.08
     Ian
    -0.08
     liaison
    -0.08
    POSITIVE LOGITS
     ratio
    0.10
     logarith
    0.09
     numerator
    0.09
    ratio
    0.09
     exponential
    0.08
     الإف
    0.08
     ratios
    0.08
    _ratio
    0.08
     Ratio
    0.08
     denominator
    0.08
    Act Density 0.070%

    No Known Activations