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

    Neuronpedia

    INDEX
    Explanations

    Identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _plugins
    -0.07
    .getID
    -0.07
     годы
    -0.07
     우리는
    -0.07
    каж
    -0.07
    алось
    -0.07
    -with
    -0.06
    network
    -0.06
     буду
    -0.06
    _manage
    -0.06
    POSITIVE LOGITS
    詩
    0.07
    azi
    0.06
     die
    0.06
     ces
    0.06
    -leg
    0.06
     midpoint
    0.06
    VER
    0.06
     proofs
    0.06
    華
    0.06
     Leh
    0.06
    Act Density 0.182%

    No Known Activations