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

    Neuronpedia

    INDEX
    Explanations

    describing things like OpenAI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    यु
    0.29
    dar
    0.28
     T
    0.25
     up
    0.25
    cur
    0.25
    ми
    0.25
    ins
    0.24
    ita
    0.24
    ago
    0.24
    кана
    0.24
    POSITIVE LOGITS
     أيض
    0.27
     διαφορε
    0.27
     Analyse
    0.26
     affirmation
    0.26
     снять
    0.26
     Antennes
    0.26
     amené
    0.26
     contractName
    0.26
     ratione
    0.26
     कॉन्फ्रेंस
    0.26
    Act Density 0.000%

    No Known Activations