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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    phrases related to national or governmental policies and their implications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Burr
    -0.06
    碼
    -0.06
    칭
    -0.06
    大利
    -0.06
    .Keys
    -0.05
     Encoding
    -0.05
    .sdk
    -0.05
     momentarily
    -0.05
    .shader
    -0.05
     الانت
    -0.05
    POSITIVE LOGITS
    ...');↵
    0.07
    577
    0.07
    arken
    0.07
    },↵↵
    0.07
     Tomáš
    0.06
    ---↵
    0.06
    '],↵
    0.06
     ),↵
    0.06
     });↵↵↵
    0.06
     застосов
    0.06
    Act Density 0.066%

    No Known Activations