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

    Neuronpedia

    INDEX
    Explanations

    transformation happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amarin
    0.42
    RING
    0.41
    CodeableConcept
    0.39
     मददगार
    0.39
    Xbox
    0.37
     живу
    0.37
    amard
    0.36
    gesamt
    0.34
     faith
    0.34
     trackers
    0.34
    POSITIVE LOGITS
    noti
    0.39
    สรร
    0.37
    ந்த
    0.36
     különb
    0.36
    spel
    0.35
     quibusdam
    0.35
    KV
    0.35
    nyj
    0.35
    開発
    0.35
    মেন
    0.35
    Act Density 0.000%

    No Known Activations