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

    Neuronpedia

    INDEX
    Explanations

    foreign language names and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🙈
    0.37
    🔷
    0.33
    ➖➖
    0.32
    🤷
    0.32
     alerg
    0.32
    🔶
    0.32
    🙊
    0.32
     hehe
    0.32
     mohou
    0.31
     pono
    0.31
    POSITIVE LOGITS
    The
    0.43
     The
    0.39
    opération
    0.36
    ά
    0.36
    ای
    0.35
    the
    0.34
    ਼
    0.33
     जोश
    0.33
     स्वागत
    0.32
     THE
    0.32
    Act Density 0.044%

    No Known Activations