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

    Neuronpedia

    INDEX
    Explanations

    four-digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iais
    -0.06
    biased
    -0.06
    _visited
    -0.06
    :async
    -0.06
    为空
    -0.06
    EDIATEK
    -0.06
     zus
    -0.06
    ตาม
    -0.06
     onemoc
    -0.06
    ом
    -0.06
    POSITIVE LOGITS
     legend
    0.07
     actor
    0.07
    agnost
    0.06
     attacks
    0.06
     arts
    0.06
     MP
    0.06
    esser
    0.06
     invites
    0.06
     coaching
    0.06
     돌
    0.06
    Act Density 0.001%

    No Known Activations