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
    *)
    0.48
    ❰
    0.48
     greatness
    0.45
    ⮕
    0.43
     idioms
    0.43
     vyr
    0.42
     plates
    0.42
     albums
    0.41
     ETH
    0.41
     syllables
    0.41
    POSITIVE LOGITS
    arı
    0.43
     encarg
    0.42
     Brothers
    0.42
    第六
    0.42
    inite
    0.41
    众人
    0.41
    ilización
    0.40
    跹
    0.40
    әй
    0.40
    導演
    0.40
    Act Density 0.000%

    No Known Activations