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

    Neuronpedia

    INDEX
    Explanations

    actions related to system operations and modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    execute commands and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.46
     narcissist
    -0.46
     decedent
    -0.45
    OGND
    -0.44
    的呢
    -0.43
    schrank
    -0.43
    aronne
    -0.41
     stället
    -0.40
    差不
    -0.40
     passphrase
    -0.40
    POSITIVE LOGITS
    }*/
    0.64
    揄
    0.63
    });*/
    0.57
    })*/
    0.56
    };*/
    0.54
    UrlResolution
    0.53
     للاسماء
    0.53
    日閲覧
    0.53
    /*
    0.52
    ing
    0.50
    Act Density 0.019%

    No Known Activations