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

    Neuronpedia

    INDEX
    Explanations

    bounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gig
    -0.08
     classifier
    -0.07
     classifiers
    -0.07
    erry
    -0.07
     Aster
    -0.07
     Gin
    -0.06
    ArrayList
    -0.06
    世紀
    -0.06
    학기
    -0.06
     usuario
    -0.06
    POSITIVE LOGITS
     bound
    0.09
     Bound
    0.08
    Bound
    0.07
    ун
    0.07
    uns
    0.07
    UNS
    0.07
    _MB
    0.07
     تاب
    0.07
     HWND
    0.07
    _HOLD
    0.07
    Act Density 0.016%

    No Known Activations