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

    Neuronpedia

    INDEX
    Explanations

    who or whose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    チャレンジ
    1.23
    ést
    1.18
    દર્શન
    1.18
    ジュ
    1.18
     ఆలో
    1.16
    Comté
    1.16
     masyarakat
    1.15
     essentiels
    1.15
     kehidupan
    1.14
    ステ
    1.14
    POSITIVE LOGITS
     from
    1.22
     in
    1.21
     with
    1.19
     as
    1.19
     a
    1.14
     whose
    1.13
     at
    1.11
     for
    1.08
     if
    1.07
     on
    1.07
    Act Density 0.000%

    No Known Activations