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

    Neuronpedia

    INDEX
    Explanations

    wife or she actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allis
    -0.09
    nown
    -0.09
    祥
    -0.09
     thrown
    -0.09
    ouz
    -0.08
    uxtap
    -0.08
    685
    -0.08
     Affero
    -0.08
    ิร
    -0.08
    ëĭĪëĭ¤
    -0.08
    POSITIVE LOGITS
    ç»ĻæĪij
    0.19
    让æĪij
    0.17
     told
    0.14
     me
    0.14
     rám
    0.13
    æĺ¯æĪij
    0.13
     мне
    0.12
     tôi
    0.11
    æĪij
    0.11
     seemed
    0.11
    Act Density 0.154%

    No Known Activations