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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Annex
    -0.07
     lombok
    -0.06
     примен
    -0.06
     blocking
    -0.06
     diarrhea
    -0.06
    iliki
    -0.06
     fq
    -0.06
     ib
    -0.06
    yang
    -0.06
    ารย
    -0.06
    POSITIVE LOGITS
    ×
    0.07
    AsStringAsync
    0.06
     М
    0.06
     coax
    0.06
     Suppose
    0.06
     Ultra
    0.06
     ค
    0.06
     reconnaissance
    0.06
    Ben
    0.06
     purchasers
    0.06
    Act Density 0.004%

    No Known Activations