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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mits
    -0.07
     сообщ
    -0.07
    -season
    -0.06
    IZER
    -0.06
    itzer
    -0.06
     refugee
    -0.06
    ца
    -0.06
    Gs
    -0.06
     healed
    -0.06
    	let
    -0.06
    POSITIVE LOGITS
    908
    0.07
    /cpp
    0.06
     wohl
    0.06
    _ary
    0.06
     *)
    0.06
    970
    0.06
    Không
    0.06
    ////////
    0.06
     sesso
    0.06
    Jo
    0.06
    Act Density 0.012%

    No Known Activations