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

    Neuronpedia

    INDEX
    Explanations

    eclipse IDE and related projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.96
    る
    0.91
    ase
    0.80
    I
    0.79
    ag
    0.75
    ai
    0.75
     лишь
    0.75
    ala
    0.74
    ali
    0.74
    lier
    0.73
    POSITIVE LOGITS
    ↵
    1.22
    ల
    0.89
     Eclipse
    0.86
    ج
    0.86
     Meinung
    0.84
    나
    0.84
     Wirtschaft
    0.83
    ير
    0.83
     not
    0.82
    ميل
    0.82
    Act Density 0.001%

    No Known Activations