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

    Neuronpedia

    INDEX
    Explanations

    C library, system calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Stiff
    -0.75
    Dome
    -0.75
     Ammonia
    -0.74
     UPSC
    -0.73
    KIL
    -0.72
    orca
    -0.72
    ývá
    -0.72
     orna
    -0.71
    BANG
    -0.71
     lacquered
    -0.71
    POSITIVE LOGITS
     javafx
    0.74
    eltzer
    0.73
    سي
    0.71
    libc
    0.69
     específicos
    0.68
     xong
    0.68
     desee
    0.68
     específica
    0.67
     libc
    0.67
    whatever
    0.66
    Act Density 0.195%

    No Known Activations