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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elcome
    -0.07
     использовани
    -0.06
    اليا
    -0.06
     GridLayout
    -0.06
    (balance
    -0.06
     влад
    -0.06
     said
    -0.06
    _then
    -0.06
    迎
    -0.06
     стоя
    -0.06
    POSITIVE LOGITS
    Through
    0.10
     Through
    0.10
     through
    0.09
     THROUGH
    0.09
    -through
    0.09
    through
    0.08
     COMPLETE
    0.07
    _additional
    0.07
     діяль
    0.07
     celou
    0.06
    Act Density 0.011%

    No Known Activations