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

    Neuronpedia

    INDEX
    Explanations

    OR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _wire
    -0.07
    /Dk
    -0.07
    šen
    -0.06
    +N
    -0.06
     declaring
    -0.06
    .testing
    -0.06
     Kenn
    -0.06
    ْف
    -0.06
    (sh
    -0.06
    _bi
    -0.06
    POSITIVE LOGITS
     обличчя
    0.07
     그가
    0.07
    ريق
    0.07
    战斗
    0.06
     القد
    0.06
    ổi
    0.06
     sensation
    0.06
     Claude
    0.06
    `)↵
    0.06
    anonymous
    0.06
    Act Density 0.001%

    No Known Activations