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

    Neuronpedia

    INDEX
    Explanations

    need, to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     r
    -0.08
    	rec
    -0.07
     ability
    -0.06
    	op
    -0.06
    Sites
    -0.06
     forgiven
    -0.06
     positives
    -0.06
    Offline
    -0.06
     Purs
    -0.06
     rooft
    -0.06
    POSITIVE LOGITS
    .Category
    0.07
    _EDGE
    0.07
     Ella
    0.07
     сьогодні
    0.07
     Sawyer
    0.07
    AVED
    0.07
    鐘
    0.06
    ею
    0.06
     diagrams
    0.06
    /system
    0.06
    Act Density 0.003%

    No Known Activations