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

    Neuronpedia

    INDEX
    Explanations

    text generation examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     banks
    -0.09
     refurbished
    -0.08
     тиг
    -0.08
    ೆಯ
    -0.08
     yacc
    -0.08
     확보
    -0.08
     bends
    -0.08
    �
    -0.07
     bank
    -0.07
     refurbishment
    -0.07
    POSITIVE LOGITS
     subsets
    0.13
     subset
    0.11
    subset
    0.10
    -empty
    0.10
    Subset
    0.09
     selective
    0.08
     vider
    0.08
     Empty
    0.08
    Empty
    0.08
     [[]
    0.08
    Act Density 0.036%

    No Known Activations