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

    Neuronpedia

    INDEX
    Explanations

    courses and exams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fu
    -0.07
     chua
    -0.07
    	IN
    -0.06
    throw
    -0.06
    ﺘ
    -0.06
     Gods
    -0.06
     Nut
    -0.06
    components
    -0.06
    ový
    -0.06
    "But
    -0.06
    POSITIVE LOGITS
     Intelli
    0.07
     prototype
    0.06
    IFICATE
    0.06
     VERBOSE
    0.06
    declspec
    0.06
    ание
    0.06
    radient
    0.06
    AuthToken
    0.06
    ْت
    0.06
    れて
    0.06
    Act Density 0.008%

    No Known Activations