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

    Neuronpedia

    INDEX
    Explanations

    terms and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Clément
    0.41
    obranch
    0.41
     vyb
    0.40
     vybaven
    0.39
    sklär
    0.39
     ગૃહ
    0.39
     dispositif
    0.38
     LGBTQ
    0.38
     instruções
    0.38
    🚮
    0.38
    POSITIVE LOGITS
     গো
    0.45
    天
    0.43
    爱
    0.42
     Tasty
    0.40
    进口
    0.40
     এখনও
    0.39
    自定义
    0.38
     විට
    0.38
    脸
    0.38
     Token
    0.37
    Act Density 0.000%

    No Known Activations