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

    Neuronpedia

    INDEX
    Explanations

    java code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一個
    1.00
    ar
    0.92
    ជា
    0.83
    т
    0.81
     constellations
    0.80
    ي
    0.80
    му
    0.80
    atma
    0.79
     middlewares
    0.78
    ل
    0.78
    POSITIVE LOGITS
     potrz
    0.99
    ﻙ
    0.89
    k
    0.83
    kite
    0.81
    小数
    0.80
    ˨
    0.80
    イト
    0.77
    ruptcy
    0.76
    grasp
    0.76
     forn
    0.76
    Act Density 0.004%

    No Known Activations