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

    Neuronpedia

    INDEX
    Explanations

    fractions and proportions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uição
    -0.08
    ATED
    -0.07
    oundary
    -0.07
     Plymouth
    -0.07
    лата
    -0.06
    ated
    -0.06
    -eight
    -0.06
    inated
    -0.06
    ilerin
    -0.06
    associ
    -0.06
    POSITIVE LOGITS
    ordable
    0.06
    結婚
    0.06
     carb
    0.06
    Half
    0.06
     Rach
    0.06
    .Serial
    0.06
     kin
    0.06
    (userData
    0.06
     Rodney
    0.06
     denomin
    0.06
    Act Density 0.008%

    No Known Activations