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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shield
    -0.07
     quartz
    -0.07
     kterém
    -0.07
    <Type
    -0.07
     penalty
    -0.07
    嘴
    -0.07
     City
    -0.06
     Storm
    -0.06
    Thickness
    -0.06
    ра�
    -0.06
    POSITIVE LOGITS
    retorno
    0.07
    OUS
    0.06
    REP
    0.06
    olean
    0.06
    oubles
    0.06
    ritis
    0.06
    Submitted
    0.06
     الإسلام
    0.06
    oppins
    0.06
    (mail
    0.06
    Act Density 0.014%

    No Known Activations