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

    Neuronpedia

    INDEX
    Explanations

    finding best options/context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᅥ
    0.47
    教
    0.45
     Plants
    0.45
    ipfs
    0.44
     pod
    0.44
     occurs
    0.44
    í
    0.44
     dosa
    0.43
     zh
    0.43
    disco
    0.43
    POSITIVE LOGITS
    зне
    0.45
    ز
    0.45
    iovas
    0.45
    ன்
    0.43
     бе
    0.43
     veineux
    0.42
     untouched
    0.42
     бай
    0.41
     оружия
    0.41
    neş
    0.41
    Act Density 0.001%

    No Known Activations