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

    Neuronpedia

    INDEX
    Explanations

    turn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )("
    -0.07
    .Security
    -0.06
     understand
    -0.06
    کور
    -0.06
     prix
    -0.06
    rowth
    -0.06
    _pressure
    -0.06
    _ENC
    -0.06
     sought
    -0.06
    ladığı
    -0.06
    POSITIVE LOGITS
     прев
    0.07
    しまう
    0.07
     ترب
    0.06
     Mirage
    0.06
     تبدیل
    0.06
     roar
    0.06
     Laud
    0.06
     trick
    0.06
    tit
    0.06
    经营
    0.06
    Act Density 0.030%

    No Known Activations