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

    Neuronpedia

    INDEX
    Explanations

    punctuation/end of phrase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulation
    -0.07
     Authentication
    -0.07
    Pot
    -0.07
    ать
    -0.06
     ostat
    -0.06
    Euro
    -0.06
     Citizen
    -0.06
     assemblies
    -0.06
     characterized
    -0.06
     напри
    -0.06
    POSITIVE LOGITS
    )^
    0.07
    ?>"></
    0.07
     *)__
    0.07
    .Suppress
    0.07
    )(__
    0.07
     */↵↵↵
    0.06
    239
    0.06
     پیوند
    0.06
    ,sizeof
    0.06
    celed
    0.06
    Act Density 0.000%

    No Known Activations