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

    Neuronpedia

    INDEX
    Explanations

    conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Atlantis
    0.48
    ).
    0.46
     chl
    0.46
    0.46
    0.46
     Enrico
    0.45
    TI
    0.44
     .-
    0.44
    .)
    0.43
     Edward
    0.43
    POSITIVE LOGITS
    വൃത്തി
    0.46
    yawa
    0.45
     послу
    0.44
    ᱔
    0.43
    Singolare
    0.42
    યોગ
    0.42
    キャッシュ
    0.42
    ल्व
    0.42
    yzed
    0.41
    フルーツ
    0.41
    Act Density 0.002%

    No Known Activations