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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     맛
    -0.06
     PBS
    -0.06
     drag
    -0.06
    živ
    -0.06
    <b
    -0.06
     sed
    -0.06
     trails
    -0.06
     Pediatric
    -0.06
    ikleri
    -0.06
     Question
    -0.06
    POSITIVE LOGITS
    ymph
    0.07
     Texans
    0.07
     nướng
    0.06
    99
    0.06
    ありがとう
    0.06
     spac
    0.06
    난
    0.06
    (lua
    0.06
    485
    0.06
    093
    0.06
    Act Density 0.004%

    No Known Activations