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

    Neuronpedia

    INDEX
    Explanations

    screen capture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Save
    -0.07
    (predict
    -0.06
    _reverse
    -0.06
    Increasing
    -0.06
     مت
    -0.06
    _vert
    -0.06
     measuring
    -0.06
    levance
    -0.06
     modulo
    -0.06
    	byte
    -0.06
    POSITIVE LOGITS
     Kob
    0.06
    urbation
    0.06
    姓名
    0.06
    acting
    0.06
    traits
    0.06
    -U
    0.06
     помощ
    0.06
    �u
    0.06
    person
    0.06
    renal
    0.06
    Act Density 0.008%

    No Known Activations