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

    Neuronpedia

    INDEX
    Explanations

    say "equal signs"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Considering
    -0.07
    ولي
    -0.07
     Political
    -0.07
     Iceland
    -0.07
     Institutions
    -0.07
    ربية
    -0.07
     bishops
    -0.06
    etten
    -0.06
     contraception
    -0.06
    kept
    -0.06
    POSITIVE LOGITS
     footprint
    0.07
    ç
    0.07
    :["
    0.07
    pageNum
    0.07
    oxide
    0.07
    Elem
    0.07
     rooting
    0.07
    _p
    0.06
    "use
    0.06
    .DAO
    0.06
    Act Density 0.010%

    No Known Activations