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

    Neuronpedia

    INDEX
    Explanations

    suction cup mount, Maglev trains, Hyperloop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     r
    0.68
     l
    0.67
     can
    0.61
     origami
    0.57
     parabolic
    0.55
     n
    0.54
     stru
    0.54
     m
    0.53
    up
    0.53
     gru
    0.53
    POSITIVE LOGITS
    েলের
    0.61
    Inicial
    0.61
    大
    0.61
    kiyor
    0.61
    がいる
    0.60
     ਸਿੰਘ
    0.59
    []);
    0.56
     கிஷ
    0.56
     იყოს
    0.56
    BrNO
    0.56
    Act Density 0.003%

    No Known Activations