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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GGLE
    -0.07
    alic
    -0.06
    ستان
    -0.06
    ΑΝ
    -0.06
    IRT
    -0.06
    #####↵
    -0.06
    gold
    -0.06
     itching
    -0.06
     ripped
    -0.06
    gili
    -0.06
    POSITIVE LOGITS
     декіль
    0.07
     logical
    0.07
     徒歩
    0.07
    	Returns
    0.07
     Otto
    0.06
    _common
    0.06
    ıntı
    0.06
     тро
    0.06
     achter
    0.06
     vigorously
    0.06
    Act Density 0.024%

    No Known Activations