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

    Neuronpedia

    INDEX
    Explanations

    .c and .h files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ليس
    -0.07
    �
    -0.07
     Timothy
    -0.07
    INGS
    -0.07
    툇
    -0.07
     Ну
    -0.07
    XR
    -0.06
    .deep
    -0.06
    䂮
    -0.06
     下
    -0.06
    POSITIVE LOGITS
     architecture
    0.08
     resonate
    0.08
     confort
    0.08
    isti
    0.07
    .getLabel
    0.07
    _atom
    0.07
     ovar
    0.07
     Artist
    0.07
    異なる
    0.07
     [.
    0.06
    Act Density 0.006%

    No Known Activations