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

    Neuronpedia

    INDEX
    Explanations

    X-Men

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     readiness
    -0.06
    作为
    -0.06
    >'
    -0.06
    @
    -0.06
    書館
    -0.06
     Cumberland
    -0.06
    Sent
    -0.06
     stehen
    -0.06
     piles
    -0.06
     cone
    -0.06
    POSITIVE LOGITS
     Wolverine
    0.07
    94
    0.07
     Trou
    0.07
    miner
    0.06
     Cách
    0.06
    -Men
    0.06
     Fallout
    0.06
     X
    0.06
    .New
    0.06
    InputChange
    0.06
    Act Density 0.003%

    No Known Activations