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

    Neuronpedia

    INDEX
    Explanations

    youtube script generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unscrupulous
    0.34
     fouls
    0.33
     bolt
    0.30
     casualties
    0.30
     emergent
    0.29
     hadron
    0.29
     scorers
    0.29
     depred
    0.29
     analges
    0.29
     blemishes
    0.29
    POSITIVE LOGITS
    Youtube
    0.40
     유튜브
    0.35
    動画
    0.35
    ```
    0.35
    Okay
    0.34
    Here
    0.33
    أ
    0.33
    youtube
    0.32
    kira
    0.31
     videolar
    0.31
    Act Density 0.001%

    No Known Activations