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

    Neuronpedia

    INDEX
    Explanations

    violence and dragging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOSS
    -0.08
    _TCP
    -0.07
     +(
    -0.07
     passé
    -0.06
    _pat
    -0.06
     caz
    -0.06
     pan
    -0.06
     vouchers
    -0.06
     para
    -0.06
    la
    -0.06
    POSITIVE LOGITS
     vape
    0.07
    subj
    0.06
     Больш
    0.06
    	Date
    0.06
     enticing
    0.06
     airl
    0.06
    alyzer
    0.06
     DataService
    0.06
    uell
    0.06
    yclerview
    0.06
    Act Density 0.007%

    No Known Activations