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

    Neuronpedia

    INDEX
    Explanations

    code structures and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    3.05
    на
    2.70
    ம்
    2.06
    我
    2.05
    ן
    2.05
    م
    1.93
    न
    1.85
    انج
    1.82
    zelfde
    1.79
    א
    1.79
    POSITIVE LOGITS
    it
    2.55
    un
    2.41
    t
    2.02
    ac
    1.94
    LE
    1.81
    sight
    1.80
    iant
    1.78
    ik
    1.77
    iniz
    1.77
    tive
    1.73
    Act Density 0.130%

    No Known Activations