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

    Neuronpedia

    INDEX
    Explanations

    list or definition start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ெடு
    0.46
    ুজ
    0.45
     lisse
    0.44
     carène
    0.43
    BOAT
    0.42
     lijn
    0.42
    牽
    0.42
    脷
    0.41
     zorgt
    0.41
     récomp
    0.41
    POSITIVE LOGITS
    n
    0.53
    icias
    0.50
     redefined
    0.49
    icient
    0.48
    imized
    0.48
     examined
    0.46
     exploring
    0.46
    ijing
    0.46
    st
    0.46
    e
    0.46
    Act Density 0.001%

    No Known Activations