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

    Neuronpedia

    INDEX
    Explanations

    flavorful food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trouver
    0.46
     selectively
    0.45
    将
    0.45
     finding
    0.45
     textile
    0.44
    ل
    0.44
    的选择
    0.43
    െങ്ക
    0.42
     '+':
    0.42
    ரத்தில்
    0.42
    POSITIVE LOGITS
    𝗵
    0.54
    IZA
    0.53
    TRAS
    0.52
    0.49
    ão
    0.47
    ˀ
    0.47
    MET
    0.46
    𝘃
    0.45
     Лон
    0.44
    UNDO
    0.44
    Act Density 0.001%

    No Known Activations