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

    Neuronpedia

    INDEX
    Explanations

    policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rich
    -0.08
    azen
    -0.07
     Preston
    -0.07
    огда
    -0.07
    sex
    -0.07
    thro
    -0.06
    (Test
    -0.06
    gu
    -0.06
     geçmiş
    -0.06
    омина
    -0.06
    POSITIVE LOGITS
     policy
    0.08
    .device
    0.07
    policy
    0.06
    -policy
    0.06
     Session
    0.06
    .Parser
    0.06
     Δ
    0.06
    	perror
    0.06
    经理
    0.06
     کردن
    0.06
    Act Density 0.002%

    No Known Activations