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

    Neuronpedia

    INDEX
    Explanations

    processes and technical terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eben
    -0.07
    ıp
    -0.06
     ":"
    -0.06
     inner
    -0.06
     cruise
    -0.06
     oath
    -0.06
    .cols
    -0.06
     LOGGER
    -0.06
    ReadStream
    -0.06
     ResourceBundle
    -0.06
    POSITIVE LOGITS
    -P
    0.11
    -F
    0.10
    -d
    0.10
    -A
    0.10
    -H
    0.10
    -D
    0.09
    -B
    0.09
    -b
    0.09
    -s
    0.09
    -c
    0.09
    Act Density 1.260%

    No Known Activations