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

    Neuronpedia

    INDEX
    Explanations

    actions/details/concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दशक
    0.39
    ominator
    0.39
     powierzchni
    0.38
    いている
    0.35
    イズ
    0.35
     decade
    0.34
     dynast
    0.34
    Adorable
    0.34
    猖
    0.34
    フォル
    0.34
    POSITIVE LOGITS
     esp
    0.42
     Flügel
    0.42
     רבי
    0.40
    ép
    0.39
    િક્ષ
    0.39
     बाएं
    0.39
     signings
    0.39
    uana
    0.38
     چپ
    0.38
     સ્વા
    0.38
    Act Density 0.000%

    No Known Activations