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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     머
    -0.08
    anya
    -0.07
    azu
    -0.07
    inar
    -0.07
     '''
    -0.07
     DateFormatter
    -0.07
    iner
    -0.07
    transactions
    -0.07
    Ta
    -0.07
     устройства
    -0.06
    POSITIVE LOGITS
    Portrait
    0.06
     Sergei
    0.06
    each
    0.06
    Incoming
    0.06
    	for
    0.06
    available
    0.05
     Battle
    0.05
    -bs
    0.05
    tel
    0.05
     rotterdam
    0.05
    Act Density 0.039%

    No Known Activations