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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    otřeb
    -0.07
    微软雅黑
    -0.06
    allows
    -0.06
    038
    -0.06
    Restore
    -0.06
     علی
    -0.06
    .ser
    -0.06
    atis
    -0.06
     Scarlet
    -0.06
    POSITIVE LOGITS
     "))↵
    0.07
    .DriverManager
    0.06
    erville
    0.06
     tạm
    0.06
    eq
    0.06
    .helpers
    0.06
     hashlib
    0.06
    blob
    0.06
     Transcript
    0.06
     Recruitment
    0.06
    Act Density 0.000%

    No Known Activations