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

    Neuronpedia

    INDEX
    Explanations

    National Helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NAN
    0.67
    Gin
    0.64
     bax
    0.64
     ufficiale
    0.63
     GAN
    0.63
     personal
    0.63
     اوف
    0.63
     BERN
    0.63
    蔓
    0.62
     mannit
    0.61
    POSITIVE LOGITS
     ট
    0.65
     Tri
    0.64
     По
    0.60
    лү
    0.59
    Tri
    0.58
     поду
    0.58
     Tomás
    0.55
     threes
    0.54
     Tomas
    0.54
     Reservations
    0.54
    Act Density 0.083%

    No Known Activations