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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     く
    -0.06
     alloys
    -0.06
    _minus
    -0.06
    adığı
    -0.06
    laştır
    -0.06
    tığını
    -0.06
     Kata
    -0.05
    РСР
    -0.05
     diarrhea
    -0.05
     todd
    -0.05
    POSITIVE LOGITS
    	BIT
    0.07
    (elem
    0.07
     Stripe
    0.07
    计算
    0.07
    (set
    0.06
    Derived
    0.06
    	trace
    0.06
    (dummy
    0.06
    ovala
    0.06
     Architect
    0.06
    Act Density 0.132%

    No Known Activations