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

    Neuronpedia

    INDEX
    Explanations

    specific categories of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.55
     e
    0.52
     vis
    0.50
    将
    0.49
     I
    0.49
    宗
    0.45
    ار
    0.45
    و
    0.44
    H
    0.43
    로
    0.43
    POSITIVE LOGITS
    kfollowers
    0.59
    kyverno
    0.53
    texto
    0.50
    adihi
    0.49
    Flicky
    0.49
    壹章
    0.48
    Results
    0.48
    outcome
    0.48
    Gosudarstvennyj
    0.48
     मायणी
    0.48
    Act Density 0.001%

    No Known Activations