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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Os
    -0.07
     serene
    -0.06
    _EQUAL
    -0.06
    Is
    -0.06
    burn
    -0.06
     دوست
    -0.06
    stra
    -0.06
     Hakk
    -0.06
     نبود
    -0.06
    أ
    -0.06
    POSITIVE LOGITS
    FOR
    0.08
     allowable
    0.07
     gears
    0.06
    ahrain
    0.06
     levy
    0.06
     Alberta
    0.06
    theon
    0.06
     memorandum
    0.06
    RefCount
    0.06
     scrap
    0.06
    Act Density 0.020%

    No Known Activations