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

    Neuronpedia

    INDEX
    Explanations

    Article snippets

    np_max-act · gemini-2.0-flash

    The neuron detects explanatory list structures—especially when text introduces or enumerates reasons or numbered points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     needless
    -0.06
    elve
    -0.06
    олж
    -0.06
     podmínky
    -0.06
     vyj
    -0.06
     incorporate
    -0.06
     limitless
    -0.06
     gefunden
    -0.06
    Ship
    -0.06
    Reducers
    -0.06
    POSITIVE LOGITS
    ンバ
    0.07
    _unicode
    0.07
     kval
    0.07
    osyal
    0.07
    KNOWN
    0.06
    어나
    0.06
     ง
    0.06
    _atom
    0.06
    ุส
    0.06
     Tòa
    0.06
    Act Density 0.160%

    No Known Activations