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

    Neuronpedia

    INDEX
    Explanations

    Drug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _reward
    -0.08
    份
    -0.06
    ایی
    -0.06
     compares
    -0.06
    ghi
    -0.06
     compare
    -0.06
    (cards
    -0.06
    slt
    -0.06
    ροι
    -0.06
    стр
    -0.06
    POSITIVE LOGITS
    ellant
    0.07
    Gamma
    0.06
     О
    0.06
    中央
    0.06
    	dx
    0.06
    linux
    0.06
    add
    0.06
     mathematical
    0.06
    Daniel
    0.06
    .HttpServletRequest
    0.06
    Act Density 0.007%

    No Known Activations