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

    Neuronpedia

    INDEX
    Explanations

    Sea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wrath
    -0.06
    .live
    -0.06
    BIG
    -0.06
     DESC
    -0.06
    /km
    -0.06
    ôm
    -0.06
     сест
    -0.06
     knife
    -0.06
     вла
    -0.05
    enco
    -0.05
    POSITIVE LOGITS
    subscription
    0.07
     Petit
    0.07
     Baltimore
    0.07
    (example
    0.07
     Canary
    0.07
    sampling
    0.06
     rgb
    0.06
     Malaysian
    0.06
     Registered
    0.06
    ]</
    0.06
    Act Density 0.008%

    No Known Activations