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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ोष
    -0.07
    درس
    -0.07
    <thead
    -0.07
    ilip
    -0.06
     değerlendir
    -0.06
     soát
    -0.06
     dbHelper
    -0.06
    =edge
    -0.06
    ınca
    -0.06
    ulaire
    -0.06
    POSITIVE LOGITS
    ={!
    0.08
    	il
    0.06
    �
    0.06
    Rol
    0.06
    ź
    0.06
    659
    0.06
    	cs
    0.06
    LOUR
    0.06
     demonstrators
    0.06
    YLES
    0.06
    Act Density 0.005%

    No Known Activations