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

    Neuronpedia

    INDEX
    Explanations

    programming code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weil
    -0.06
     演
    -0.06
     Reform
    -0.06
     ř
    -0.06
     uncertain
    -0.06
     fieldValue
    -0.06
     جمهوری
    -0.06
    цію
    -0.06
     надання
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _callable
    0.07
     launching
    0.06
     класс
    0.06
     CZ
    0.06
     ekip
    0.06
     fullest
    0.06
    メント
    0.06
    raise
    0.06
    WORD
    0.06
     invo
    0.06
    Act Density 0.044%

    No Known Activations