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

    Neuronpedia

    INDEX
    Explanations

    Ar / Arc / Arch / Ark words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ♩
    0.44
     amer
    0.40
    बर्ग
    0.40
    ফতার
    0.38
     شناخت
    0.38
    ษัท
    0.38
    odiazep
    0.38
    斯坦
    0.38
    有很多
    0.37
    namespaces
    0.37
    POSITIVE LOGITS
     AR
    0.72
     Ar
    0.70
     ar
    0.65
     Ар
    0.62
     आर्
    0.62
     ар
    0.60
     アー
    0.59
    itecture
    0.58
    Ar
    0.57
    Arc
    0.56
    Act Density 0.052%

    No Known Activations