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

    Neuronpedia

    INDEX
    Explanations

    Question words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bảng
    -0.07
    _LOW
    -0.06
     ------>
    -0.06
     ServiceException
    -0.06
    perfect
    -0.06
     fakat
    -0.06
    duplicate
    -0.06
    _deriv
    -0.06
    <>↵
    -0.06
    nout
    -0.06
    POSITIVE LOGITS
    芳
    0.07
     Ор
    0.07
    .Adam
    0.06
     wellbeing
    0.06
    asonic
    0.06
    481
    0.06
    .reporting
    0.06
     inch
    0.06
    _USE
    0.06
     consciousness
    0.06
    Act Density 0.100%

    No Known Activations