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

    Neuronpedia

    INDEX
    Explanations

    countries/nationalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Template
    -0.08
     persönlich
    -0.07
     fleur
    -0.07
    /action
    -0.07
    많
    -0.07
     싶
    -0.07
     stuff
    -0.07
     cra
    -0.07
     laps
    -0.07
     Fibonacci
    -0.07
    POSITIVE LOGITS
    -wide
    0.11
    wide
    0.10
    共产党
    0.09
     government's
    0.08
     সরকারের
    0.08
    ’après
    0.08
    Wide
    0.08
    aved
    0.08
     expatri
    0.07
     entero
    0.07
    Act Density 0.130%

    No Known Activations