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

    Neuronpedia

    INDEX
    Explanations

    bow down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Feign
    0.40
    KeyValue
    0.38
     previewBuilder
    0.38
    职业
    0.38
    Shake
    0.37
    再去
    0.37
     sequences
    0.37
    uparavant
    0.36
    ClassObject
    0.36
    AppCompat
    0.36
    POSITIVE LOGITS
    耐
    0.46
    чного
    0.37
     والمع
    0.37
     mêmes
    0.37
     耐
    0.37
     mint
    0.36
     grams
    0.36
     أك
    0.36
     ویکی
    0.36
     enduring
    0.35
    Act Density 0.000%

    No Known Activations