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

    Neuronpedia

    INDEX
    Explanations

    coordinates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     piv
    -0.06
     propositions
    -0.06
    _den
    -0.06
     told
    -0.06
    تك
    -0.06
     Мак
    -0.06
     phased
    -0.06
    оту
    -0.06
     hut
    -0.06
    POSITIVE LOGITS
     tempfile
    0.07
    .GetMapping
    0.07
    Slug
    0.07
     доз
    0.07
     mutlu
    0.06
    -window
    0.06
     strftime
    0.06
     NSStringFromClass
    0.06
    _keys
    0.06
    CppMethod
    0.06
    Act Density 0.006%

    No Known Activations