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

    Neuronpedia

    INDEX
    Explanations

    mutable data types or outputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semblent
    0.41
    امة
    0.38
     Moskau
    0.38
     Maur
    0.38
    امات
    0.38
     Sval
    0.38
    ܝ
    0.37
     styles
    0.37
    entraî
    0.37
    圴
    0.37
    POSITIVE LOGITS
    膾
    0.39
    णा
    0.39
     AO
    0.39
     aos
    0.38
    jeff
    0.38
    焼き
    0.37
    すぎて
    0.37
    逅
    0.36
    オーバー
    0.36
    شنا
    0.35
    Act Density 0.000%

    No Known Activations