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

    Neuronpedia

    INDEX
    Explanations

    least/range followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝟕
    0.81
    ?“
    0.80
     Mesmo
    0.78
     Warsz
    0.76
     AppMethodBeat
    0.76
     $(`.
    0.76
    Ꮢ
    0.75
    𝐼
    0.75
     एपल
    0.74
    Ꭻ
    0.73
    POSITIVE LOGITS
    ผ่าน
    0.73
    手順
    0.63
     ethical
    0.63
     gaps
    0.62
     spectacular
    0.61
    ration
    0.61
    fälle
    0.61
     πολλά
    0.61
    ம்
    0.60
    हून
    0.59
    Act Density 0.001%

    No Known Activations