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

    Neuronpedia

    INDEX
    Explanations

    competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    520
    -0.07
    Records
    -0.07
     HM
    -0.06
    Explicit
    -0.06
    벌
    -0.06
    Hard
    -0.06
     Bal
    -0.06
    	cnt
    -0.06
    Effects
    -0.06
     BUS
    -0.06
    POSITIVE LOGITS
     Pane
    0.07
     ashamed
    0.07
    _LEAVE
    0.07
     closeButton
    0.07
     forControlEvents
    0.06
     neob
    0.06
     whisper
    0.06
     IconButton
    0.06
    asje
    0.06
    paced
    0.06
    Act Density 0.089%

    No Known Activations