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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (am
    -0.06
     kul
    -0.06
     dazu
    -0.06
     keto
    -0.06
    _FEED
    -0.06
     ไ
    -0.06
     руки
    -0.06
     analysed
    -0.05
    Homepage
    -0.05
    Ｃ
    -0.05
    POSITIVE LOGITS
    ाहत
    0.07
    !',↵
    0.07
     IMPORTANT
    0.07
    !”
    0.07
     Majority
    0.07
    ="")↵
    0.06
     Instruction
    0.06
    یستم
    0.06
    /rest
    0.06
    .addRow
    0.06
    Act Density 0.000%

    No Known Activations