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

    Neuronpedia

    INDEX
    Explanations

    compiled code and logging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ianSpace
    0.43
     Coulter
    0.42
    䢁
    0.41
    ಿದ್ದೇನೆ
    0.40
    蟒
    0.40
     UnitTest
    0.39
     нәрсә
    0.39
     पॉलिटी
    0.39
     ऑफिश
    0.39
    toctree
    0.38
    POSITIVE LOGITS
    Java
    0.41
    advanced
    0.41
     Java
    0.39
    extension
    0.38
    single
    0.38
    冷
    0.38
    ft
    0.37
    hot
    0.37
    idents
    0.37
     voork
    0.37
    Act Density 0.000%

    No Known Activations