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

    Neuronpedia

    INDEX
    Explanations

    beyond recycling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ocurrido
    0.44
     perfe
    0.41
     getUsers
    0.40
     storylines
    0.40
     getter
    0.40
    льзова
    0.39
     الذي
    0.39
     полного
    0.39
     yang
    0.39
     desej
    0.39
    POSITIVE LOGITS
    ipynb
    0.40
    鴟
    0.40
     twofold
    0.39
     Blob
    0.39
    вів
    0.39
    ethanol
    0.39
    कद
    0.38
     મી
    0.38
    aidh
    0.38
     Urea
    0.37
    Act Density 0.003%

    No Known Activations