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

    Neuronpedia

    INDEX
    Explanations

    beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wake
    -2.22
    wake
    -1.94
     awake
    -1.90
     waking
    -1.83
     wakes
    -1.79
     awaken
    -1.77
     woken
    -1.73
     awakening
    -1.65
     Wake
    -1.59
     awakens
    -1.59
    POSITIVE LOGITS
    y
    0.66
     in
    0.52
     to
    0.52
    id
    0.51
     di
    0.50
    ,
    0.48
    f
    0.48
     staff
    0.48
    di
    0.48
     from
    0.47
    Act Density 0.341%

    No Known Activations