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

    Neuronpedia

    INDEX
    Explanations

    ultimate source of power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    milliseconds
    0.44
     форме
    0.39
    Cursor
    0.39
     ظِلِّ
    0.39
    otu
    0.37
    უნქ
    0.37
    wicz
    0.36
    Arnold
    0.36
     દિવસ
    0.36
    イヤ
    0.35
    POSITIVE LOGITS
     drove
    0.38
     hiking
    0.38
     balcon
    0.34
     hiked
    0.33
     sacking
    0.33
     storyboard
    0.33
     rere
    0.32
     retr
    0.32
     mig
    0.32
     continues
    0.32
    Act Density 0.002%

    No Known Activations