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

    Neuronpedia

    INDEX
    Explanations

    html href attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fran
    0.46
    inando
    0.41
    naked
    0.39
    lipidemia
    0.37
    OAc
    0.37
    Fax
    0.37
    getClassName
    0.37
     dirigés
    0.37
    فر
    0.36
     señ
    0.36
    POSITIVE LOGITS
    ="./
    0.88
     "./
    0.87
    ="/
    0.83
     ./
    0.78
     "/
    0.75
    "./
    0.73
    https
    0.72
     './
    0.70
     assets
    0.68
    ='./
    0.67
    Act Density 0.005%

    No Known Activations