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

    Neuronpedia

    INDEX
    Explanations

    captions and subtitles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.31
    á
    1.20
    "
    1.20
    ↵↵
    1.16
    y
    1.16
     että
    1.10
    o
    1.09
     än
    1.08
    }
    1.08
    ก
    1.08
    POSITIVE LOGITS
    ал
    1.33
    ことなく
    1.24
    ر
    1.23
    იკ
    1.20
    こと
    1.16
    ។
    1.16
    ል።
    1.14
    لين
    1.14
     Теперь
    1.12
     Лю
    1.11
    Act Density 0.001%

    No Known Activations