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

    Neuronpedia

    INDEX
    Explanations

    winning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sacr
    -0.08
    -filter
    -0.07
    ского
    -0.07
    pj
    -0.06
     vanity
    -0.06
    destroy
    -0.06
     Control
    -0.06
    parity
    -0.06
    .media
    -0.06
    Invariant
    -0.06
    POSITIVE LOGITS
    andır
    0.07
    서울
    0.07
     의해
    0.06
    	memset
    0.06
    (DWORD
    0.06
    倫
    0.06
    ;amp
    0.06
    伦
    0.06
    남도
    0.06
     knot
    0.06
    Act Density 0.013%

    No Known Activations