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

    Neuronpedia

    INDEX
    Explanations

    complex contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    אנ
    0.33
    l
    0.30
    larının
    0.30
    אַר
    0.30
    ע
    0.30
    λιο
    0.29
    ták
    0.29
    uk
    0.29
    bö
    0.29
    ইউ
    0.28
    POSITIVE LOGITS
     melhores
    0.31
    ಮಗೆ
    0.29
     unquestion
    0.29
     Sự
    0.29
    ]`
    0.28
     fleste
    0.28
     아직
    0.28
     puns
    0.28
    Csvg
    0.28
     Как
    0.27
    Act Density 2.045%

    No Known Activations