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

    Neuronpedia

    INDEX
    Explanations

    better

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advocates
    -0.07
    irth
    -0.07
     ResponseEntity
    -0.07
    collections
    -0.06
     Ones
    -0.06
    backgroundColor
    -0.06
     POINT
    -0.06
     juxtap
    -0.06
    ..."↵↵
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     hiring
    0.06
    _restrict
    0.06
    něji
    0.06
    Wi
    0.06
     refrigerator
    0.06
     typu
    0.06
    Catch
    0.06
     bye
    0.06
    _FIFO
    0.06
    기에
    0.06
    Act Density 0.014%

    No Known Activations