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

    Neuronpedia

    INDEX
    Explanations

    dynamic conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dried
    0.39
     SOL
    0.38
     SQLite
    0.37
    设计
    0.37
    ேன்
    0.37
     swell
    0.37
     exchanging
    0.37
    ꯤ
    0.37
     dễ
    0.37
     внед
    0.37
    POSITIVE LOGITS
    isiaj
    0.42
    otification
    0.41
    noch
    0.41
    wyr
    0.41
    plaatst
    0.40
    жают
    0.40
     marais
    0.39
     publicados
    0.39
    fertigt
    0.39
    pots
    0.38
    Act Density 0.000%

    No Known Activations