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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    激活
    -0.07
    荃
    -0.07
     suppl
    -0.07
    땅
    -0.07
     Reggie
    -0.07
     fasting
    -0.07
    _AM
    -0.07
    בני
    -0.07
    ","+
    -0.07
    ﺖ
    -0.07
    POSITIVE LOGITS
    esson
    0.07
    eurs
    0.07
     impro
    0.07
    dots
    0.07
    �
    0.07
    為了
    0.07
    芟
    0.06
     prompt
    0.06
    难
    0.06
     measure
    0.06
    Act Density 0.000%

    No Known Activations