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

    Neuronpedia

    INDEX
    Explanations

    hello, greetings, and common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лод
    0.94
    TeXAtom
    0.93
    挸
    0.93
    נ
    0.93
    น
    0.91
    стіше
    0.91
    ЛЬ
    0.90
    砻
    0.90
    STRUCTIONS
    0.89
    นิด
    0.89
    POSITIVE LOGITS
     a
    1.14
     the
    1.13
     а
    1.09
     وتح
    1.05
     Não
    1.01
     cât
    1.01
     pà
    1.01
     flurry
    0.99
     hér
    0.98
     schnelle
    0.98
    Act Density 0.601%

    No Known Activations