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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     व
    -0.07
    .J
    -0.07
     Oxford
    -0.06
    .settings
    -0.06
    marshaller
    -0.06
     ราย
    -0.06
    ราย
    -0.06
    Spacing
    -0.06
     bearing
    -0.06
     rozvoj
    -0.06
    POSITIVE LOGITS
     rencontrer
    0.07
     authDomain
    0.07
    ctrine
    0.07
     zastup
    0.07
    banks
    0.06
     сам
    0.06
    ¤¤
    0.06
     collections
    0.06
    }]
    0.06
    ulnerable
    0.06
    Act Density 0.017%

    No Known Activations