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

    Neuronpedia

    INDEX
    Explanations

    code execution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пару
    -0.08
    (key
    -0.08
     코드
    -0.07
    Paragraph
    -0.07
    pletely
    -0.06
     Esther
    -0.06
    타
    -0.06
    parency
    -0.06
    idon
    -0.06
    (entity
    -0.06
    POSITIVE LOGITS
    ."]↵
    0.07
    	pos
    0.07
    ULL
    0.07
     ymax
    0.06
    "]↵
    0.06
     policym
    0.06
     ],
↵
    0.06
    *******
↵
    0.06
    ....↵
    0.06
     ASF
    0.06
    Act Density 0.003%

    No Known Activations