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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vements
    -0.07
     medicinal
    -0.07
    של
    -0.07
    	del
    -0.07
    kas
    -0.07
     Casinos
    -0.06
     G
    -0.06
     laws
    -0.06
    ipzig
    -0.06
    UNKNOWN
    -0.06
    POSITIVE LOGITS
     CUSTOM
    0.08
    OutOfRangeException
    0.07
     Tradable
    0.07
    UTTON
    0.07
    顾客
    0.07
     sympathetic
    0.07
    uib
    0.06
     infographic
    0.06
     sama
    0.06
     עצמי
    0.06
    Act Density 0.092%

    No Known Activations