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

    Neuronpedia

    INDEX
    Explanations

    GPT 3.5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    猗
    0.47
    Ａ
    0.44
    ística
    0.43
    ••••
    0.41
    ರ
    0.38
    AN
    0.38
    Assertion
    0.38
    sphinx
    0.38
     آئینے
    0.38
    графия
    0.37
    POSITIVE LOGITS
     इंजन
    0.50
     precision
    0.46
     Vintage
    0.42
     Precision
    0.42
     Strasbourg
    0.41
     Vinci
    0.40
     elegant
    0.39
     vintage
    0.38
     Delivery
    0.38
     convo
    0.38
    Act Density 0.005%

    No Known Activations