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

    Neuronpedia

    INDEX
    Explanations

    understanding and impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    诙
    0.48
    chus
    0.46
    dasarkan
    0.44
    自由
    0.44
    웰
    0.43
    檚
    0.43
    5
    0.42
    I
    0.42
    ﺷ
    0.42
    7
    0.42
    POSITIVE LOGITS
     longo
    0.45
     Bridge
    0.45
     вовсе
    0.44
    Exe
    0.43
     Granada
    0.43
    InCM
    0.43
     muita
    0.42
     รู้
    0.42
     前
    0.42
    াজী
    0.41
    Act Density 0.001%

    No Known Activations