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

    Neuronpedia

    INDEX
    Explanations

    Academic papers/research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    主義
    -0.07
     Period
    -0.07
    izations
    -0.06
     pne
    -0.06
     anlayış
    -0.06
    fft
    -0.06
    isations
    -0.06
    ічної
    -0.06
     plastics
    -0.06
    カテ
    -0.06
    POSITIVE LOGITS
    рес
    0.07
    -conf
    0.06
    stopped
    0.06
     ش
    0.06
     QStringList
    0.06
     Writes
    0.06
     JAXB
    0.06
    ờ
    0.06
     Tunnel
    0.05
    .ax
    0.05
    Act Density 0.032%

    No Known Activations