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

    Neuronpedia

    INDEX
    Explanations

    theorem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _traffic
    -0.08
     dubious
    -0.08
    يتها
    -0.07
     postage
    -0.07
    ETIME
    -0.07
    广播电视
    -0.07
    Including
    -0.07
    LIKE
    -0.07
     "('
    -0.07
    Sad
    -0.07
    POSITIVE LOGITS
     theorem
    0.09
     pragma
    0.07
    本钱
    0.07
    صم
    0.06
     memo
    0.06
     mundo
    0.06
    otte
    0.06
     sinc
    0.06
    	config
    0.06
    큼
    0.06
    Act Density 0.004%

    No Known Activations