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

    Neuronpedia

    INDEX
    Explanations

    news/ national

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leaves
    0.43
     Leaves
    0.41
    bble
    0.41
     toxin
    0.40
    ্যাপ
    0.38
    Leaves
    0.38
     клет
    0.37
     Neuro
    0.37
     neuro
    0.36
     heat
    0.36
    POSITIVE LOGITS
     нацыяна
    0.44
    national
    0.44
    世
    0.44
     nacional
    0.42
    全國
    0.42
    ∗
    0.41
    ].[
    0.41
     نیشنل
    0.41
     nasional
    0.40
     Nacional
    0.39
    Act Density 0.002%

    No Known Activations