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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getStatus
    -0.07
    The
    -0.07
    .Override
    -0.06
    .ud
    -0.06
    .bc
    -0.06
     Inc
    -0.06
    етод
    -0.06
    GameState
    -0.06
     The
    -0.06
    agy
    -0.06
    POSITIVE LOGITS
     decided
    0.07
     seiner
    0.06
     val
    0.06
     TED
    0.06
     СП
    0.06
    grams
    0.06
     studying
    0.06
     serv
    0.06
     Fah
    0.06
    ITS
    0.06
    Act Density 0.099%

    No Known Activations