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

    Neuronpedia

    INDEX
    Explanations

    Vicuna model versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     S
    0.73
     الس
    0.59
     הס
    0.56
    S
    0.48
     ސ
    0.47
    𝑆
    0.47
     স
    0.46
     Sasha
    0.42
     Sá
    0.42
     ಸ
    0.42
    POSITIVE LOGITS
     thirteen
    0.58
     fourteen
    0.54
     fifteen
    0.50
     v
    0.48
     Thirteen
    0.48
     twelve
    0.44
     Fourteen
    0.44
     १३
    0.43
    十三
    0.41
    lín
    0.41
    Act Density 0.026%

    No Known Activations