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

    Neuronpedia

    INDEX
    Explanations

    conversational quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    or
    1.02
    on
    0.89
    in
    0.88
    ou
    0.73
    ين
    0.72
    ers
    0.70
    op
    0.67
    for
    0.62
    and
    0.61
    amp
    0.61
    POSITIVE LOGITS
     dabb
    0.75
     kawaida
    0.68
     griev
    0.65
     bele
    0.63
     Govt
    0.62
     gerecht
    0.62
     coisa
    0.62
    喏
    0.61
     Hollywood
    0.60
     haut
    0.60
    Act Density 3.723%

    No Known Activations