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

    Neuronpedia

    INDEX
    Explanations

    GraalVM native compilation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icus
    0.39
    ையோ
    0.39
    Jeh
    0.38
    漪
    0.38
    োরে
    0.38
    AsStream
    0.38
     मैट्रिक
    0.37
     custody
    0.37
    ার্থীর
    0.37
     abducted
    0.37
    POSITIVE LOGITS
    Gra
    0.56
     Gra
    0.56
    loadNpmTasks
    0.41
    gra
    0.39
    nails
    0.39
     gra
    0.36
     Todor
    0.36
    pang
    0.36
    idik
    0.36
    svm
    0.35
    Act Density 0.004%

    No Known Activations