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

    Neuronpedia

    INDEX
    Explanations

    URLs and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    möglich
    0.43
    ín
    0.36
    Pressed
    0.36
     from
    0.36
    hearted
    0.36
     právě
    0.35
    ite
    0.34
    ara
    0.34
     for
    0.34
    ited
    0.34
    POSITIVE LOGITS
     taea
    0.36
    𝖊
    0.34
    σιμοποι
    0.33
     onus
    0.32
    тали
    0.32
    ');//
    0.32
    但他
    0.32
     ಸಾಮಾನ್ಯವಾಗಿ
    0.31
     elastomer
    0.31
    ]='
    0.31
    Act Density 0.003%

    No Known Activations