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

    Neuronpedia

    INDEX
    Explanations

    supports and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sinn
    0.37
    сынын
    0.36
    ग्ध
    0.36
    譲
    0.34
    acotta
    0.34
     எழுந்த
    0.34
     compon
    0.34
     स्त्रीलिंग
    0.34
    ButtonGroup
    0.34
     बरबाद
    0.33
    POSITIVE LOGITS
    支持
    2.53
     support
    2.45
     supports
    2.42
    support
    2.41
    supports
    2.31
     지원
    2.31
    Support
    2.30
    Supports
    2.25
     Supports
    2.20
     suport
    2.20
    Act Density 0.174%

    No Known Activations