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

    Neuronpedia

    INDEX
    Explanations

    end of explanatory sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     уйнагыз
    0.31
    などで
    0.31
    なども
    0.29
    ಗ
    0.28
     của
    0.26
    ୟ
    0.25
     लागि
    0.25
    х
    0.25
    для
    0.25
    ங்கும்
    0.24
    POSITIVE LOGITS
    。
    0.44
    .
    0.34
    ။
    0.30
    。“
    0.29
    ።
    0.29
    ｡
    0.29
     Its
    0.29
    ۔
    0.29
    ។
    0.29
     มัน
    0.29
    Act Density 0.964%

    No Known Activations