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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lanç
    -0.08
    вей
    -0.07
    μές
    -0.06
     хотел
    -0.06
     للإ
    -0.06
     Php
    -0.06
     Shank
    -0.06
    	scanf
    -0.06
     ingin
    -0.06
     possui
    -0.06
    POSITIVE LOGITS
    _install
    0.07
     boob
    0.06
    故事
    0.06
     dose
    0.06
    V
    0.06
    Iterator
    0.06
    隠
    0.06
    har
    0.06
    �
    0.06
     CJ
    0.06
    Act Density 0.013%

    No Known Activations