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

    Neuronpedia

    INDEX
    Explanations

    waiting or delays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    从此
    0.38
    ൊ
    0.36
     neon
    0.35
     akt
    0.34
     curv
    0.34
     constamment
    0.34
     desp
    0.33
    ဋ
    0.33
     במה
    0.33
    widths
    0.33
    POSITIVE LOGITS
     wait
    3.02
     waited
    2.81
     waits
    2.69
     Wait
    2.66
    wait
    2.55
    Wait
    2.53
     WAIT
    2.45
     waiting
    2.44
     menunggu
    2.44
     기다
    2.23
    Act Density 0.022%

    No Known Activations