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

    Neuronpedia

    INDEX
    Explanations

    impact, security, performance, support, profiling, monitoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وح
    0.47
     ذكر
    0.47
     planks
    0.47
     preguntas
    0.47
     اذا
    0.46
     أمس
    0.46
     Mick
    0.46
     أح
    0.46
     Nicky
    0.46
     leo
    0.46
    POSITIVE LOGITS
    льной
    0.42
     inhabiting
    0.42
    ᙱ
    0.42
    ਗੇ
    0.42
    erical
    0.41
     réellement
    0.41
    alph
    0.41
     inhabit
    0.41
    dering
    0.40
    fib
    0.40
    Act Density 0.000%

    No Known Activations