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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Filters
    -0.07
     Saints
    -0.07
    med
    -0.07
     кількості
    -0.07
     youth
    -0.07
    .AlertDialog
    -0.06
    KI
    -0.06
    credits
    -0.06
    $_
    -0.06
    immers
    -0.06
    POSITIVE LOGITS
    ρούν
    0.07
    �
    0.06
    	RTDBG
    0.06
    _gen
    0.06
    /small
    0.06
     Stamford
    0.06
    ющими
    0.06
     effortless
    0.06
     entrada
    0.06
    Manufact
    0.06
    Act Density 0.000%

    No Known Activations