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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mahmoud
    -0.07
    หว
    -0.06
    �
    -0.06
     نش
    -0.06
     Depression
    -0.06
    _separator
    -0.06
     Locale
    -0.06
    .Points
    -0.06
     Passport
    -0.06
     rh
    -0.06
    POSITIVE LOGITS
     rise
    0.07
     dram
    0.07
    ์ได
    0.07
    _regularizer
    0.07
    -pol
    0.07
    _Parms
    0.07
    ANGLES
    0.06
    间
    0.06
    طلق
    0.06
    lut
    0.06
    Act Density 0.006%

    No Known Activations