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

    Neuronpedia

    INDEX
    Explanations

    free software license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     экологи
    0.75
    нд
    0.70
    ÃO
    0.70
    gins
    0.69
    MBOL
    0.69
     integração
    0.69
    MLL
    0.68
     कंप्यूट
    0.66
    ↵↵
    0.65
     eukaryotic
    0.65
    POSITIVE LOGITS
    ımda
    0.84
    ım
    0.83
    我已经
    0.82
    ımın
    0.82
    ic
    0.82
    俺
    0.81
    િવસે
    0.80
    Notable
    0.80
    いない
    0.80
     yo
    0.79
    Act Density 0.002%

    No Known Activations