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

    Neuronpedia

    INDEX
    Explanations

    closing messages and conversational interjections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     counterparts
    0.63
     counterpart
    0.58
     nomads
    0.58
     মামলায়
    0.58
    ুল
    0.58
     makeshift
    0.58
     nominating
    0.57
    verband
    0.57
    selectors
    0.57
    SETTINGS
    0.57
    POSITIVE LOGITS
     Exactly
    1.39
     Oh
    1.37
    Oh
    1.33
     Yeah
    1.30
     Precis
    1.30
     We
    1.27
    Yeah
    1.23
     Tôi
    1.19
     Okay
    1.18
    Exactly
    1.18
    Act Density 0.001%

    No Known Activations