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

    Neuronpedia

    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words ending in “-ing,” i.e. gerund or present-participle verb forms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     meanwhile
    -0.07
     제가
    -0.07
    (hash
    -0.07
     pien
    -0.07
    <decimal
    -0.06
     wait
    -0.06
     CancellationToken
    -0.06
    (category
    -0.06
    _public
    -0.06
     Địa
    -0.06
    POSITIVE LOGITS
     salv
    0.07
     GLint
    0.06
    机械
    0.06
     striking
    0.06
    แบบ
    0.06
    ामन
    0.06
    gar
    0.06
    Highlighted
    0.06
    авлива
    0.05
     itertools
    0.05
    Act Density 0.048%

    No Known Activations