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

    Neuronpedia

    INDEX
    Explanations

    contrasting clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hype
    0.41
     encomendas
    0.36
    )}/>
    0.35
    诸多
    0.35
     sayfası
    0.35
    ން
    0.35
     shenanigans
    0.35
    ताई
    0.35
     kiddos
    0.35
    喲
    0.35
    POSITIVE LOGITS
     considering
    0.79
     being
    0.71
     without
    0.68
     namely
    0.66
     moreover
    0.66
     leaving
    0.65
     although
    0.64
     taking
    0.64
    being
    0.64
    considering
    0.63
    Act Density 0.002%

    No Known Activations