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

    Neuronpedia

    INDEX
    Explanations

    information seeking, personal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ූ
    0.41
    둬
    0.40
     일어나
    0.39
     ifstream
    0.39
    谯
    0.38
    Исто
    0.37
    嬬
    0.37
    |_{\
    0.37
    棿
    0.37
     ########
    0.36
    POSITIVE LOGITS
     Bache
    0.38
     problem
    0.38
     사고
    0.37
     centro
    0.37
    ί
    0.37
     Reilly
    0.37
     Hanson
    0.35
     Cher
    0.35
     Ward
    0.35
    ultur
    0.35
    Act Density 0.038%

    No Known Activations