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

    Neuronpedia

    INDEX
    Explanations

    magic trick descriptions/reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ungalow
    -0.08
     jde
    -0.07
    UART
    -0.06
     územ
    -0.06
    '''
    -0.06
    oard
    -0.06
    çon
    -0.06
    Ext
    -0.06
     BY
    -0.06
    ’acc
    -0.06
    POSITIVE LOGITS
    PEndPoint
    0.06
     auditing
    0.06
    central
    0.06
     ﺍ
    0.06
     transactions
    0.06
     mekan
    0.06
    řít
    0.05
     defaults
    0.05
     learner
    0.05
     π
    0.05
    Act Density 0.010%

    No Known Activations