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

    Neuronpedia

    INDEX
    Explanations

    web code and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     i
    0.54
     endeavors
    0.49
     enjoying
    0.48
     endeavours
    0.46
     appears
    0.45
     eks
    0.45
     pretende
    0.44
     Exclusive
    0.44
     on
    0.43
     congratulations
    0.43
    POSITIVE LOGITS
    Whe
    0.54
    인
    0.49
    Protein
    0.49
    По
    0.48
    Pourquoi
    0.48
    직
    0.47
    یکشن
    0.47
     किडनी
    0.47
    قول
    0.46
    Ե
    0.46
    Act Density 0.000%

    No Known Activations