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

    Neuronpedia

    INDEX
    Explanations

    python string operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.67
    é
    0.51
    是一款
    0.50
     fasi
    0.49
    oram
    0.48
    t
    0.48
     сверх
    0.48
    เสนอ
    0.47
    am
    0.46
     вен
    0.46
    POSITIVE LOGITS
    Η
    0.57
    ıya
    0.51
    jte
    0.48
    íte
    0.47
     throwIfNotFound
    0.47
    瑯
    0.46
     inorder
    0.46
    禕
    0.46
    賚
    0.46
     ज्ञात
    0.45
    Act Density 0.000%

    No Known Activations