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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Although
    -0.07
     お
    -0.07
    Proc
    -0.07
    Lifetime
    -0.06
    asan
    -0.06
    HasColumnType
    -0.06
    	while
    -0.06
    ![↵
    -0.06
    暂
    -0.06
    -config
    -0.06
    POSITIVE LOGITS
     Duc
    0.07
    redients
    0.07
     melted
    0.07
    /items
    0.07
    Baby
    0.07
     Scale
    0.06
     Di
    0.06
     DIY
    0.06
     Statement
    0.06
    :D
    0.06
    Act Density 0.001%

    No Known Activations