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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้ด
    -0.07
     dedim
    -0.07
    .pause
    -0.07
    .MapPath
    -0.07
    esus
    -0.06
    ANS
    -0.06
    says
    -0.06
    .onView
    -0.06
     περ
    -0.06
    _derivative
    -0.06
    POSITIVE LOGITS
    SM
    0.07
     GV
    0.07
    064
    0.06
    см
    0.06
     Ale
    0.06
    Assistant
    0.06
     Kashmir
    0.06
     бел
    0.06
     uphold
    0.06
     těž
    0.06
    Act Density 0.014%

    No Known Activations