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

    Neuronpedia

    INDEX
    Explanations

    ize

    np_max-act · gemini-2.0-flash

    The neuron is activated by the suffix “ize,” i.e. it detects words ending with “ize.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unless
    -0.07
     dart
    -0.07
     acts
    -0.07
     hold
    -0.06
     occult
    -0.06
     ought
    -0.06
     sixth
    -0.06
     letting
    -0.06
     achieving
    -0.06
     let
    -0.06
    POSITIVE LOGITS
    ize
    0.16
    ized
    0.14
    ization
    0.13
    izes
    0.12
    iz
    0.12
    IZ
    0.11
    IZED
    0.11
    ise
    0.11
    izing
    0.11
    из
    0.11
    Act Density 0.131%

    No Known Activations