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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash

    The neuron fires on words and short phrases that signal emerging or growing evidence or recognition (e.g. “increasingly,” “growing,” “evidence suggests,” “recognized as”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _vertical
    -0.07
     překvap
    -0.07
     ksi
    -0.06
    ізнес
    -0.06
     Laurent
    -0.06
     geld
    -0.06
     Drill
    -0.06
    %%%
    -0.06
    μένη
    -0.06
     ﾊ
    -0.06
    POSITIVE LOGITS
     розум
    0.07
     Cardinals
    0.07
     Prescription
    0.07
     userDetails
    0.06
     Matcher
    0.06
    [target
    0.06
     protože
    0.06
                                 ↵
    0.06
     Independence
    0.06
     efficacy
    0.06
    Act Density 0.060%

    No Known Activations