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

    Neuronpedia

    INDEX
    Explanations

    However, is, the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    说明
    0.44
     scoperto
    0.41
     Yours
    0.41
     मैदान
    0.41
     Afro
    0.40
     पुराने
    0.38
     صار
    0.38
     sufrimiento
    0.38
     Guan
    0.38
     stating
    0.38
    POSITIVE LOGITS
    bern
    0.42
     diffusive
    0.41
    ppins
    0.40
     लौटे
    0.38
    phere
    0.38
     উদ্ভিদ
    0.38
    ох
    0.38
    $.}
    0.38
    ousine
    0.37
     pegged
    0.37
    Act Density 0.000%

    No Known Activations