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

    Neuronpedia

    INDEX
    Explanations

    ob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivor
    -0.07
     программы
    -0.07
     Cookbook
    -0.07
     gala
    -0.07
    走出去
    -0.07
     institute
    -0.07
    ổi
    -0.07
     ye
    -0.06
     Blocks
    -0.06
    еньк
    -0.06
    POSITIVE LOGITS
    	RTLR
    0.07
    _rat
    0.07
    ◌
    0.07
    	best
    0.07
    聂
    0.07
     EditText
    0.06
    夫妻
    0.06
     \""
    0.06
     Based
    0.06
    \Category
    0.06
    Act Density 0.001%

    No Known Activations