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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tember
    -0.07
    (candidate
    -0.07
    (Chat
    -0.06
    .Inst
    -0.06
    	rect
    -0.06
    busters
    -0.06
     managers
    -0.06
    DialogTitle
    -0.06
    XC
    -0.06
     ambigu
    -0.06
    POSITIVE LOGITS
     диагности
    0.07
    =((
    0.07
    (data
    0.06
    無しさん
    0.06
    著
    0.06
     Aberdeen
    0.06
    })(
    0.06
    $(
    0.06
     ordeal
    0.06
    µ
    0.06
    Act Density 0.050%

    No Known Activations