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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     выбра
    -0.07
     Learned
    -0.07
     realizado
    -0.07
     Vũ
    -0.07
     사업
    -0.06
    าระ
    -0.06
     COMPUT
    -0.06
     Melissa
    -0.06
    Raised
    -0.06
     PRICE
    -0.06
    POSITIVE LOGITS
     copies
    0.09
     سن
    0.07
     Norton
    0.07
    Γ
    0.06
    PreferredGap
    0.06
     Ea
    0.06
    sage
    0.06
     destroyer
    0.06
     ін
    0.06
     copy
    0.06
    Act Density 0.006%

    No Known Activations