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

    Neuronpedia

    INDEX
    Explanations

    ize/ization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     should
    -0.07
     occult
    -0.07
     retains
    -0.07
     may
    -0.07
     fact
    -0.07
     although
    -0.07
     affect
    -0.07
     elif
    -0.07
     affiliate
    -0.07
     Both
    -0.07
    POSITIVE LOGITS
    ize
    0.17
    ized
    0.16
    ization
    0.14
    izing
    0.13
    izes
    0.13
    ised
    0.13
    IZED
    0.12
    IZATION
    0.11
    isation
    0.11
    iz
    0.10
    Act Density 0.164%

    No Known Activations