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

    Neuronpedia

    INDEX
    Explanations

    ideology and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    吝
    1.21
    බැ
    1.17
    intage
    1.15
    orderBy
    1.15
    webContents
    1.13
    isSignedIn
    1.13
    𒈾
    1.13
     `<=
    1.12
    𒂵
    1.12
    ਫ਼
    1.11
    POSITIVE LOGITS
    in
    1.17
    ar
    0.96
    but
    0.91
     calming
    0.90
     senc
    0.90
     LIV
    0.87
    er
    0.87
    けど
    0.87
     sendo
    0.86
    -
    0.85
    Act Density 0.000%

    No Known Activations