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

    Neuronpedia

    INDEX
    Explanations

    Smithsonian science articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     via
    0.69
     so
    0.67
     behind
    0.66
     their
    0.64
     der
    0.64
     i
    0.63
     being
    0.63
    ु
    0.62
     gifted
    0.61
     either
    0.61
    POSITIVE LOGITS
     Economía
    0.91
    ጺ
    0.86
    យ៉
    0.85
    频谱
    0.83
     ആരാധ
    0.82
    elementProp
    0.82
    ontan
    0.81
    ঞ্জাম
    0.81
    යක
    0.80
    Ȼ
    0.80
    Act Density 0.008%

    No Known Activations