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

    Neuronpedia

    INDEX
    Explanations

    iterating lists being modified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     milk
    -0.08
    يس
    -0.08
    ulf
    -0.07
    URA
    -0.07
    Sure
    -0.07
     MUCH
    -0.07
     "',
    -0.07
    PUTE
    -0.07
    ale
    -0.07
    field
    -0.07
    POSITIVE LOGITS
    สอง
    0.09
    netinet
    0.07
     인간
    0.07
    /set
    0.07
    であろう
    0.06
     interceptions
    0.06
    constants
    0.06
    连接
    0.06
    _Draw
    0.06
     onStop
    0.06
    Act Density 0.018%

    No Known Activations