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

    Neuronpedia

    INDEX
    Explanations

    code and syntax examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Helena
    -0.07
     towels
    -0.07
    NSSet
    -0.07
    	al
    -0.07
     smirk
    -0.07
    masına
    -0.07
     butt
    -0.07
     Ballard
    -0.06
     Candle
    -0.06
     IntelliJ
    -0.06
    POSITIVE LOGITS
    شن
    0.06
    =G
    0.06
    []
    0.06
    _YELLOW
    0.06
    economic
    0.06
     accompanies
    0.06
    :n
    0.06
     physical
    0.06
     phot
    0.06
     grounded
    0.06
    Act Density 0.009%

    No Known Activations