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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the modal verb “can” (often in conditional/ability constructions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -model
    -0.07
    Fetch
    -0.06
     SYSTEM
    -0.06
     skin
    -0.06
    Mode
    -0.06
    _dialog
    -0.06
    afety
    -0.06
     Bedford
    -0.06
    Span
    -0.06
     Benny
    -0.06
    POSITIVE LOGITS
     Identifier
    0.06
    ाहत
    0.06
    ERGE
    0.06
    abile
    0.06
    _NONNULL
    0.06
    由
    0.06
     Mehmet
    0.06
     जम
    0.06
    ーブ
    0.05
    olve
    0.05
    Act Density 0.018%

    No Known Activations