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

    Neuronpedia

    INDEX
    Explanations

    confusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     litre
    -0.07
    т
    -0.07
     Vick
    -0.07
     diligence
    -0.06
     Sector
    -0.06
    -day
    -0.06
     gig
    -0.06
    -types
    -0.06
    lrt
    -0.06
    406
    -0.06
    POSITIVE LOGITS
     confusion
    0.14
     confusing
    0.11
     confused
    0.11
     confuse
    0.09
     guides
    0.08
     dizzy
    0.07
     concerned
    0.07
     friend
    0.07
    混
    0.07
     Blues
    0.07
    Act Density 0.012%

    No Known Activations