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

    Neuronpedia

    INDEX
    Explanations

    retrieved from web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Uno
    0.42
    Jackson
    0.40
    Una
    0.38
    Bing
    0.38
    Cher
    0.36
    Según
    0.36
    uno
    0.35
     Walker
    0.34
    Hallo
    0.34
     नम
    0.34
    POSITIVE LOGITS
     $<\
    0.52
     〈
    0.50
     \<
    0.50
     $<$
    0.49
    ウェブ
    0.48
     [<
    0.47
     website
    0.47
     वेबसाइट
    0.47
     веб
    0.47
     web
    0.46
    Act Density 0.000%

    No Known Activations