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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Woman
    -0.07
    .localtime
    -0.07
     cannon
    -0.07
    (integer
    -0.07
     DE
    -0.06
     TAKE
    -0.06
     میان
    -0.06
    )이
    -0.06
    	f
    -0.06
    PROJECT
    -0.06
    POSITIVE LOGITS
    ibern
    0.06
    /movie
    0.06
    agement
    0.06
     unfit
    0.06
    _supplier
    0.06
    ぎ
    0.06
    alah
    0.06
    รายการ
    0.06
    /load
    0.06
     Context
    0.05
    Act Density 0.035%

    No Known Activations