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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sí
    -0.07
    復
    -0.07
    Unsupported
    -0.07
    statusCode
    -0.07
    ramework
    -0.07
     throughout
    -0.07
    뜹
    -0.06
    '")↵
    -0.06
    fü
    -0.06
    ﭑ
    -0.06
    POSITIVE LOGITS
     wave
    0.07
     позволя
    0.07
    bucket
    0.07
    人力
    0.07
    .isArray
    0.06
    邱
    0.06
     ambient
    0.06
    iox
    0.06
     Builder
    0.06
     Silver
    0.06
    Act Density 0.014%

    No Known Activations