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

    Neuronpedia

    INDEX
    Explanations

    printf with format string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acular
    0.43
    AuthController
    0.39
    net
    0.37
    ueba
    0.37
     February
    0.37
     catchy
    0.36
    IDAD
    0.36
     आकर्षक
    0.35
     الجديدة
    0.35
     november
    0.34
    POSITIVE LOGITS
     आसन
    0.43
    仃
    0.42
     منہ
    0.41
     থাকিতে
    0.41
    மூ
    0.41
     Holes
    0.41
     Amn
    0.40
    πή
    0.40
    瞽
    0.40
     तिल
    0.40
    Act Density 0.001%

    No Known Activations