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

    Neuronpedia

    INDEX
    Explanations

    computational terms and diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sophia
    0.40
    Someone
    0.40
    eseorang
    0.40
    ội
    0.39
     使っ
    0.38
    Emails
    0.38
    人士
    0.36
    Jane
    0.35
    ACCOUNT
    0.35
    Karen
    0.35
    POSITIVE LOGITS
     axisymmetric
    0.47
     ekki
    0.47
     non
    0.46
     C
    0.41
     only
    0.41
    沒有
    0.41
     ২
    0.40
     ikinci
    0.40
     G
    0.40
     endast
    0.39
    Act Density 0.036%

    No Known Activations