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

    Neuronpedia

    INDEX
    Explanations

    c standard library include

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paise
    0.40
     rodents
    0.39
     정리
    0.38
    覃
    0.38
    CNc
    0.38
     отды
    0.38
    ೇವೆ
    0.38
    бры
    0.38
     shelters
    0.37
    빡
    0.37
    POSITIVE LOGITS
     EXIT
    0.69
     exit
    0.65
    exit
    0.64
    EXIT
    0.64
    Exit
    0.64
     Exit
    0.64
     exits
    0.54
     exited
    0.51
    Environmental
    0.49
     malloc
    0.48
    Act Density 0.000%

    No Known Activations