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

    Neuronpedia

    INDEX
    Explanations

    through theatrical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    粒子
    0.46
     Zahn
    0.46
     eti
    0.42
     بودند
    0.42
     Hamiltonian
    0.41
     semic
    0.41
     unnamed
    0.41
     neuromuscular
    0.41
     perturbation
    0.41
     coupling
    0.40
    POSITIVE LOGITS
     Cómo
    0.54
    Cómo
    0.44
     ತಯ
    0.43
    Cách
    0.42
     maig
    0.42
     如何
    0.41
     איך
    0.40
    ಶ್ರೀ
    0.39
    遨
    0.39
    kt
    0.38
    Act Density 0.000%

    No Known Activations