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

    Neuronpedia

    INDEX
    Explanations

    permits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     technically
    -0.07
    utut
    -0.07
    Encrypt
    -0.06
    '>".$
    -0.06
     stocking
    -0.06
    <>("
    -0.06
    очно
    -0.06
     součas
    -0.06
    اخ
    -0.06
     Ст
    -0.06
    POSITIVE LOGITS
    ै।↵
    0.07
     erb
    0.07
    erus
    0.06
     Cer
    0.06
    ैं।↵
    0.06
    уди
    0.06
    goo
    0.06
     veter
    0.06
    .Sin
    0.06
    Ь
    0.06
    Act Density 0.045%

    No Known Activations