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

    Neuronpedia

    INDEX
    Explanations

    gibberish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $.
    -0.07
     핵
    -0.06
    逆
    -0.06
    91
    -0.06
     форми
    -0.06
     Garner
    -0.06
    Providers
    -0.06
     Gary
    -0.06
    019
    -0.06
     Commod
    -0.06
    POSITIVE LOGITS
    ництво
    0.06
     Αρ
    0.06
    iciente
    0.06
    ooky
    0.06
     ras
    0.06
     Champagne
    0.06
    boru
    0.06
     aider
    0.06
    іш
    0.06
     assigns
    0.06
    Act Density 0.021%

    No Known Activations