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

    Neuronpedia

    INDEX
    Explanations

    reasonable expectation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oc
    0.47
    áte
    0.46
     NOVA
    0.45
    就是一个
    0.43
     Nova
    0.43
     warming
    0.42
     Assessments
    0.42
    ေါ်
    0.42
    schlag
    0.42
     YAML
    0.42
    POSITIVE LOGITS
    बंदी
    0.46
     પ્રાપ્ત
    0.44
     memperoleh
    0.42
     について
    0.42
    गम
    0.41
    то
    0.40
    био
    0.40
    to
    0.40
    кта
    0.40
     consigo
    0.40
    Act Density 0.001%

    No Known Activations