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

    Neuronpedia

    INDEX
    Explanations

    list item introducers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zent
    0.44
    z
    0.44
    lena
    0.43
     emerges
    0.40
    </td>
    0.40
    k
    0.40
     cava
    0.39
    x
    0.39
     aprox
    0.38
    ｚ
    0.38
    POSITIVE LOGITS
    തി
    0.48
    萨
    0.45
    Consistency
    0.45
     Physics
    0.42
    스트
    0.41
     Physik
    0.41
    ྒྱ
    0.40
    Absorption
    0.40
    PlayerSelector
    0.39
    リー
    0.39
    Act Density 0.001%

    No Known Activations