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

    Neuronpedia

    INDEX
    Explanations

    Types/Classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     लेख
    -0.08
    onaut
    -0.08
     investigaciones
    -0.08
     Orch
    -0.07
     ume
    -0.07
     safeguard
    -0.07
    uming
    -0.07
    .Module
    -0.07
    ज
    -0.07
    research
    -0.07
    POSITIVE LOGITS
     batches
    0.09
     ترین
    0.09
     массов
    0.09
    .bulk
    0.09
    ‌ترین
    0.09
     distint
    0.09
     bulk
    0.09
    bulk
    0.09
     herken
    0.08
    iciro
    0.08
    Act Density 0.024%

    No Known Activations