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

    Neuronpedia

    INDEX
    Explanations

    meow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🗒
    0.30
     данни
    0.30
     மணியே
    0.30
    ngrx
    0.29
    मर्रा
    0.29
    バイス
    0.28
    尼亚克
    0.28
    hci
    0.27
     rém
    0.27
    ➌
    0.27
    POSITIVE LOGITS
    0.42
    ா
    0.34
     C
    0.33
     com
    0.30
     etc
    0.30
     С
    0.29
     \
    0.29
    }$
    0.28
     </
    0.28
     Goal
    0.27
    Act Density 0.069%

    No Known Activations