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

    Neuronpedia

    INDEX
    Explanations

    between X and Y

    np_acts-logits-general · gemini-2.5-flash-lite

    lists with conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.73
    is
    0.66
    as
    0.65
    u
    0.64
    us
    0.63
    er
    0.63
    ak
    0.63
    ba
    0.60
    be
    0.59
     Excellency
    0.57
    POSITIVE LOGITS
     vacuoles
    0.69
    ﺎ
    0.63
    ен
    0.59
     mortars
    0.55
     seagulls
    0.54
    ента
    0.54
     waffles
    0.52
     motels
    0.52
    서
    0.52
    А
    0.52
    Act Density 0.222%

    No Known Activations