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

    Neuronpedia

    INDEX
    Explanations

    quick followed by an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وی
    0.50
     carbides
    0.50
    يا
    0.48
    نی
    0.48
    یا
    0.48
     œuvres
    0.47
    ರ
    0.47
    ?</
    0.47
     thermoplastics
    0.47
     šest
    0.47
    POSITIVE LOGITS
     quick
    0.49
    ↵↵
    0.48
     Quick
    0.47
    k
    0.44
    c
    0.44
     rápido
    0.43
    a
    0.43
     быстро
    0.42
    f
    0.42
    不可以
    0.42
    Act Density 0.111%

    No Known Activations