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

    Neuronpedia

    INDEX
    Explanations

    phrases and mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rež
    0.50
     zuvor
    0.47
     laboratorium
    0.46
    estinal
    0.45
     framebuffer
    0.44
     melalui
    0.44
     actualización
    0.44
     administratif
    0.44
    emura
    0.43
    बलेट
    0.43
    POSITIVE LOGITS
     mentions
    0.70
     phrases
    0.55
     synonyms
    0.54
     강조
    0.54
     Phrases
    0.49
     mentioned
    0.48
     recurring
    0.48
     언급
    0.48
     synonym
    0.46
    相关的
    0.45
    Act Density 0.056%

    No Known Activations