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

    Neuronpedia

    INDEX
    Explanations

    Common words in general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Filters
    -0.08
    _PROC
    -0.06
    entieth
    -0.06
    _AXIS
    -0.06
    paRepository
    -0.06
    ใช
    -0.06
    َر
    -0.06
     sẻ
    -0.06
     olmaktadır
    -0.06
    .qty
    -0.06
    POSITIVE LOGITS
    leep
    0.06
    icros
    0.06
     раза
    0.06
    -choice
    0.06
    Alt
    0.06
    シア
    0.06
    altura
    0.06
    iceps
    0.06
     SAY
    0.06
    volution
    0.06
    Act Density 0.290%

    No Known Activations