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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    куль
    -0.07
     pasar
    -0.06
     observer
    -0.06
    BS
    -0.06
    ./
    -0.06
     rooted
    -0.06
    flate
    -0.06
    يب
    -0.06
    教授
    -0.06
    MET
    -0.06
    POSITIVE LOGITS
    _Order
    0.07
     Hut
    0.06
    .Configure
    0.06
    	atomic
    0.06
    .Param
    0.06
     module
    0.06
     Pregnancy
    0.06
     frac
    0.06
    �
    0.06
    �
    0.05
    Act Density 0.020%

    No Known Activations