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

    Neuronpedia

    INDEX
    Explanations

    (optional)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ettha
    0.94
     Anambra
    0.91
     impasse
    0.90
    埇
    0.89
    0.89
     rameaux
    0.89
     பள்ளத்தா
    0.89
     sugarcane
    0.88
     interstitiis
    0.88
     আহসান
    0.88
    POSITIVE LOGITS
    Tele
    0.74
    British
    0.72
     Tele
    0.69
    Intel
    0.68
    League
    0.65
    족
    0.65
     try
    0.63
     British
    0.63
    Mic
    0.62
    ḥ
    0.60
    Act Density 0.013%

    No Known Activations