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

    Neuronpedia

    INDEX
    Explanations

    HTML title tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ao
    0.41
    သား
    0.38
     Maturity
    0.38
    ladesh
    0.37
     Regulatory
    0.36
     способы
    0.36
    بینی
    0.35
    किस्तान
    0.35
     Ensures
    0.35
     plugin
    0.35
    POSITIVE LOGITS
     종
    0.45
     хло
    0.43
     hodnot
    0.42
    审美
    0.42
     مش
    0.41
     과
    0.41
    アイ
    0.41
     நான்
    0.41
    ATCH
    0.40
     apolog
    0.40
    Act Density 0.003%

    No Known Activations