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
    receive
    -0.07
     Apart
    -0.07
    masters
    -0.07
    Compra
    -0.07
     reduction
    -0.06
    Command
    -0.06
     Drivers
    -0.06
     oldest
    -0.06
    .part
    -0.06
     który
    -0.06
    POSITIVE LOGITS
     высокой
    0.07
    estatus
    0.06
    予約
    0.06
    .ant
    0.06
    azel
    0.06
    ічного
    0.06
    >,</
    0.06
    ованих
    0.06
    YLON
    0.06
    roupon
    0.06
    Act Density 0.013%

    No Known Activations