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

    Neuronpedia

    INDEX
    Explanations

    fiber, milk, or millisecond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑈
    2.40
    𝑤
    2.36
    𝑠
    2.35
    𝑝
    2.19
    യി
    2.18
    odds
    2.18
    𝑑
    2.12
    ο
    2.10
    𝑃
    2.08
    心得
    2.07
    POSITIVE LOGITS
    en
    2.23
    ITARY
    2.13
     enthalpy
    2.10
     relational
    1.84
    ジュアル
    1.82
     rút
    1.81
    ิน
    1.77
     canto
    1.77
     terreno
    1.77
     tissue
    1.74
    Act Density 0.104%

    No Known Activations