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

    Neuronpedia

    INDEX
    Explanations

    Research study participation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Yu
    -0.08
     Overflow
    -0.08
    AMENT
    -0.07
    LEY
    -0.07
    /remove
    -0.07
     إعادة
    -0.07
     новые
    -0.07
    節
    -0.07
     Ukraine
    -0.07
    &(
    -0.06
    POSITIVE LOGITS
     sunscreen
    0.07
     Sexy
    0.07
     PAC
    0.07
    Ὃ
    0.07
    헵
    0.06
    丹
    0.06
    出汗
    0.06
    CppTypeDefinitionSizes
    0.06
    AVED
    0.06
    ㊙
    0.06
    Act Density 0.015%

    No Known Activations