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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     independence
    -0.07
    �
    -0.07
     durum
    -0.06
     neg
    -0.06
    Wake
    -0.06
     재
    -0.06
    _malloc
    -0.06
     tep
    -0.06
    력
    -0.06
     vytvá
    -0.06
    POSITIVE LOGITS
     tz
    0.08
     cute
    0.07
     uint
    0.07
     author
    0.07
     dives
    0.06
    STALL
    0.06
    VERR
    0.06
     incomplete
    0.06
    ेट
    0.06
    ива
    0.06
    Act Density 0.001%

    No Known Activations