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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pencils
    -0.08
    .xticks
    -0.07
     přičemž
    -0.07
     Fn
    -0.06
     verze
    -0.06
    при
    -0.06
    -offsetof
    -0.06
     Oscars
    -0.06
     Hills
    -0.06
    ’daki
    -0.06
    POSITIVE LOGITS
     membrane
    0.07
     titre
    0.06
    ейств
    0.06
    atility
    0.06
    827
    0.06
    選
    0.06
     madre
    0.06
     bag
    0.06
    에
    0.06
    ride
    0.06
    Act Density 0.004%

    No Known Activations