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

    Neuronpedia

    INDEX
    Explanations

    important words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iał
    0.41
    stimulated
    0.38
     jade
    0.38
    studded
    0.35
    hydration
    0.35
    iquen
    0.35
     mustn
    0.35
    ιλ
    0.34
     estím
    0.34
     እነ
    0.34
    POSITIVE LOGITS
     Important
    0.43
     penting
    0.43
     importante
    0.41
     importanti
    0.41
     FileManager
    0.40
     importants
    0.39
     important
    0.39
     mutu
    0.39
    Important
    0.38
     labelling
    0.38
    Act Density 0.002%

    No Known Activations