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

    Neuronpedia

    INDEX
    Explanations

    on/in

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of where files are located, especially spotting “on my local machine” or “on the remote server” style file‐location phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    043
    -0.07
    from
    -0.06
     libert
    -0.06
    Roger
    -0.06
    eries
    -0.06
    ама
    -0.06
     heavyweight
    -0.06
    hare
    -0.06
     ethn
    -0.06
     alarms
    -0.06
    POSITIVE LOGITS
     possono
    0.07
     จะ
    0.07
     نقل
    0.07
    CELER
    0.07
    _INT
    0.07
    register
    0.07
     xpath
    0.06
    _FILE
    0.06
    ViewChild
    0.06
     forIndexPath
    0.06
    Act Density 0.039%

    No Known Activations