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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    删除成功
    -0.08
    941
    -0.07
    _STAT
    -0.07
    ChildScrollView
    -0.07
    롱
    -0.06
    _CI
    -0.06
    _SHA
    -0.06
     Rath
    -0.06
    existence
    -0.06
    Mb
    -0.06
    POSITIVE LOGITS
     Rolling
    0.07
    ,max
    0.06
    jud
    0.06
    ATE
    0.06
    man
    0.06
     Fury
    0.06
    men
    0.06
     dynamic
    0.06
    logging
    0.06
     chaotic
    0.06
    Act Density 0.010%

    No Known Activations