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

    Neuronpedia

    INDEX
    Explanations

    *Need*, *possible*, *better*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    other
    0.52
    nP
    0.50
    Node
    0.47
    EPA
    0.45
    art
    0.45
    items
    0.45
    mentioned
    0.44
    ng
    0.43
    happ
    0.43
     Harwell
    0.43
    POSITIVE LOGITS
    <0xA9>
    0.49
     voorkomen
    0.48
    咵
    0.46
    溸
    0.46
    咾
    0.45
    enste
    0.44
    约束
    0.44
    深受
    0.44
     पढ़िए
    0.43
     кы
    0.43
    Act Density 0.004%

    No Known Activations