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

    Neuronpedia

    INDEX
    Explanations

    python imports with aliases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    introdu
    0.98
    Kep
    0.97
    Maz
    0.97
    Brexit
    0.97
    Innov
    0.96
    Bek
    0.96
    PhD
    0.96
    Venus
    0.96
    Western
    0.96
    Jewish
    0.95
    POSITIVE LOGITS
     None
    1.67
     len
    1.41
     False
    1.40
     str
    1.37
     True
    1.36
     np
    1.36
     isinstance
    1.29
     int
    1.27
     getattr
    1.25
     float
    1.22
    Act Density 1.025%

    No Known Activations