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

    Neuronpedia

    INDEX
    Explanations

    strength is essential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    también
    0.95
    ل
    0.94
    ୍
    0.91
    Está
    0.88
    然后
    0.88
     húmed
    0.88
    Benzyl
    0.87
     Está
    0.87
    También
    0.87
     kunt
    0.86
    POSITIVE LOGITS
     predicts
    0.84
     gained
    0.80
     flights
    0.79
     stocks
    0.77
     predictions
    0.77
    ch
    0.75
     sets
    0.75
     won
    0.73
     fonts
    0.73
     cash
    0.73
    Act Density 0.000%

    No Known Activations