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

    Neuronpedia

    INDEX
    Explanations

    scientific data reproducibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Florida
    -0.07
              ↵
    -0.07
    _damage
    -0.07
     software
    -0.07
     paso
    -0.07
     guns
    -0.06
     American
    -0.06
     Shirt
    -0.06
    -second
    -0.06
     digital
    -0.06
    POSITIVE LOGITS
    pres
    0.07
    Pres
    0.06
    .Rec
    0.06
     lạ
    0.06
    (In
    0.06
     av
    0.06
    Cur
    0.06
    оні
    0.06
     円
    0.06
    _blocking
    0.06
    Act Density 0.028%

    No Known Activations