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

    Neuronpedia

    INDEX
    Explanations

    quotation punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     испыт
    -0.07
    attering
    -0.06
    rej
    -0.06
     appalling
    -0.06
    ayload
    -0.06
    ським
    -0.06
     mü
    -0.06
     reflux
    -0.06
     bund
    -0.06
     İç
    -0.06
    POSITIVE LOGITS
    $/,
    0.07
    ネ
    0.07
     celebrating
    0.06
    】↵↵
    0.06
     Enjoy
    0.06
    jpg
    0.06
     salope
    0.06
     kidnapped
    0.06
    ,[
    0.06
     afr
    0.06
    Act Density 0.043%

    No Known Activations