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

    Neuronpedia

    INDEX
    Explanations

    you could see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prides
    0.87
     strives
    0.86
     predictors
    0.85
     robuste
    0.82
     ধারাবাহ
    0.81
     features
    0.80
     struggles
    0.80
     numerosas
    0.79
    Adaptive
    0.78
     creciente
    0.77
    POSITIVE LOGITS
     essentially
    1.80
     basically
    1.49
     Essentially
    1.48
     thereby
    1.45
    essentially
    1.41
    Essentially
    1.34
     Basically
    1.32
    相当于
    1.32
     indirectly
    1.30
     بذلك
    1.30
    Act Density 0.433%

    No Known Activations