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

    Neuronpedia

    INDEX
    Explanations

    Refusal to give something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stroke
    -0.07
     سف
    -0.07
     Burgess
    -0.07
    qed
    -0.07
    	errors
    -0.06
     marché
    -0.06
    RTC
    -0.06
    Tên
    -0.06
     Yin
    -0.06
     zur
    -0.06
    POSITIVE LOGITS
     natives
    0.07
    raising
    0.07
    (enc
    0.07
    闘
    0.07
    leave
    0.06
    _LL
    0.06
    하는
    0.06
     recovered
    0.06
    (Graph
    0.06
     >
    0.06
    Act Density 0.017%

    No Known Activations