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

    Neuronpedia

    INDEX
    Explanations

    Code, math, and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ermo
    -0.07
     Podle
    -0.07
    -hole
    -0.07
    스트
    -0.07
     slo
    -0.06
     Horse
    -0.06
    -points
    -0.06
    SP
    -0.06
     Blue
    -0.06
    _last
    -0.06
    POSITIVE LOGITS
    _ABI
    0.06
    .person
    0.06
     Constantin
    0.06
     첨부파일
    0.06
     conspic
    0.06
    (today
    0.06
     것도
    0.06
    _percentage
    0.06
    이는
    0.06
     sickness
    0.05
    Act Density 0.077%

    No Known Activations