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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    รอง
    -0.08
    	enum
    -0.07
     corazón
    -0.07
    _solve
    -0.07
     наз
    -0.07
    ץ
    -0.07
    Dar
    -0.07
    Trou
    -0.06
     sacred
    -0.06
     ._
    -0.06
    POSITIVE LOGITS
     lineman
    0.07
    สะอา
    0.07
    磷
    0.07
    iPhone
    0.06
    白马
    0.06
     לקרא
    0.06
    浙江大学
    0.06
     Islamist
    0.06
    湴
    0.06
    🏅
    0.06
    Act Density 0.008%

    No Known Activations