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

    Neuronpedia

    INDEX
    Explanations

    compile, compilation, compiling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ко
    0.42
    يرا
    0.41
    ập
    0.40
    چا
    0.39
    喧
    0.39
    áln
    0.39
     поро
    0.38
    小数点
    0.38
     ocen
    0.38
    ধিক
    0.38
    POSITIVE LOGITS
     Comp
    0.95
    Comp
    0.83
     কম্প
    0.79
     comp
    0.75
    comp
    0.69
     컴
    0.67
    COMP
    0.65
    hensive
    0.64
     Compilation
    0.64
     Kom
    0.62
    Act Density 0.022%

    No Known Activations