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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes and patterns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _acc
    -0.07
    orne
    -0.07
    Dub
    -0.07
    Javascript
    -0.07
    ويت
    -0.07
     Wr
    -0.07
    -war
    -0.07
     Auditor
    -0.07
    _PB
    -0.06
     Ada
    -0.06
    POSITIVE LOGITS
    cete
    0.06
     cél
    0.06
     kole
    0.06
     Capt
    0.06
     redundancy
    0.06
     podob
    0.06
     taught
    0.06
    -rule
    0.06
     hav
    0.06
     liegt
    0.06
    Act Density 0.092%

    No Known Activations