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

    Neuronpedia

    INDEX
    Explanations

    listing examples or inclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paymentRequest
    0.30
    琭
    0.29
     (?)
    0.29
     alcoved
    0.28
     unspoken
    0.28
     añadido
    0.27
    :[/
    0.27
     풀
    0.27
     구간
    0.27
    Wildlife
    0.27
    POSITIVE LOGITS
    including
    0.47
     including
    0.43
     culminating
    0.42
    featuring
    0.38
     exemplified
    0.38
     culminated
    0.38
    such
    0.35
    particularly
    0.35
     включая
    0.35
    namely
    0.35
    Act Density 0.006%

    No Known Activations