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

    Neuronpedia

    INDEX
    Explanations

    Software registry and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinterest
    -0.07
     LAS
    -0.06
    (an
    -0.06
    	double
    -0.06
    Descri
    -0.06
     Pompe
    -0.06
    kü
    -0.06
     surprise
    -0.06
     culture
    -0.06
     apology
    -0.06
    POSITIVE LOGITS
    resent
    0.07
    .ViewModel
    0.06
     Без
    0.06
     vzdál
    0.06
    arence
    0.06
     lasc
    0.06
    ]=='
    0.06
    χω
    0.06
    (',');↵
    0.06
     діяльність
    0.06
    Act Density 0.012%

    No Known Activations