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

    Neuronpedia

    INDEX
    Explanations

    context, tags, seed, or research areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    跗
    0.46
    ná
    0.43
    ArchivePath
    0.43
    蜘
    0.42
    мно
    0.41
    quinolin
    0.41
    aia
    0.41
     Insertion
    0.41
     CONN
    0.41
    ódio
    0.40
    POSITIVE LOGITS
     reactor
    0.46
     nord
    0.44
    லுக்கு
    0.43
    প
    0.43
     workable
    0.41
    www
    0.41
     bekommen
    0.41
    ല്ല
    0.41
    רו
    0.41
    iktok
    0.41
    Act Density 0.001%

    No Known Activations