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

    Neuronpedia

    INDEX
    Explanations

    mathematical patterns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assumptions
    -0.10
     statutory
    -0.08
     obligations
    -0.08
     guarantees
    -0.08
     prostate
    -0.07
    income
    -0.07
     misuse
    -0.07
     répar
    -0.07
     prolonged
    -0.07
     provisions
    -0.07
    POSITIVE LOGITS
     coth
    0.09
     somehow
    0.09
     einges
    0.08
    ???↵
    0.08
    _factor
    0.08
    endal
    0.08
     Fibonacci
    0.08
    factor
    0.08
    0.08
     Elias
    0.08
    Act Density 0.033%
    No Known Activations