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

    Neuronpedia

    INDEX
    Explanations

    ============

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ////////////////////////////////////////////////////////////////
    -0.08
     subur
    -0.07
    waters
    -0.07
     конкур
    -0.06
    stroke
    -0.06
     intl
    -0.06
    .pres
    -0.06
     endl
    -0.06
     tudo
    -0.06
    PrototypeOf
    -0.06
    POSITIVE LOGITS
     Raw
    0.07
    ических
    0.06
    Play
    0.06
    RAW
    0.06
     adopt
    0.06
    .channels
    0.06
    couldn
    0.06
    ICLES
    0.06
     Rules
    0.06
    _RSA
    0.06
    Act Density 0.003%

    No Known Activations