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

    Neuronpedia

    INDEX
    Explanations

    single characters and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    href
    -0.07
    .Add
    -0.06
     amps
    -0.06
     closures
    -0.06
     trò
    -0.06
     energies
    -0.06
     altına
    -0.06
    .getM
    -0.06
    }"↵
    -0.06
    :'/
    -0.06
    POSITIVE LOGITS
     Buddhist
    0.07
     Sheet
    0.06
    Installed
    0.06
    helm
    0.06
    eous
    0.06
     Erica
    0.06
    牙
    0.06
    ā
    0.06
     кон
    0.06
     Buddh
    0.06
    Act Density 0.007%

    No Known Activations