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

    Neuronpedia

    INDEX
    Explanations

    Hebrew and other languages questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     및
    0.93
    ئين
    0.90
    ٍ
    0.85
     succesfully
    0.82
     prominently
    0.81
     Inert
    0.81
     וב
    0.81
    Assume
    0.81
     ءِ
    0.81
     esclusivamente
    0.80
    POSITIVE LOGITS
    ّه
    0.92
     οποίο
    0.88
    َّ
    0.84
     chances
    0.83
     οποία
    0.83
    هم
    0.78
    َّ
    0.77
    reten
    0.76
    𝒔
    0.76
    𝒆
    0.75
    Act Density 0.001%

    No Known Activations