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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nguyện
    -0.07
    modify
    -0.06
     وفي
    -0.06
     WAN
    -0.06
    ？」
    -0.06
    ляет
    -0.06
    nictvím
    -0.06
    875
    -0.06
    _PARSE
    -0.06
     говорить
    -0.06
    POSITIVE LOGITS
    ape
    0.07
    ATAB
    0.07
     produced
    0.06
     Assess
    0.06
     Token
    0.06
    implement
    0.06
     deepen
    0.06
     Produce
    0.06
    .code
    0.06
    Direct
    0.06
    Act Density 0.000%

    No Known Activations