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

    Neuronpedia

    INDEX
    Explanations

    opinions, questions

    np_max-act · gemini-2.0-flash

    The neuron fires on informal, vague quantifier phrases that begin general statements (e.g. “a lot of what’s…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ницы
    -0.07
     Gardner
    -0.07
     cott
    -0.07
     abl
    -0.06
    chooser
    -0.06
     Variant
    -0.06
     tomato
    -0.06
    _sc
    -0.06
    meld
    -0.06
    ْر
    -0.06
    POSITIVE LOGITS
    ted
    0.06
     Фед
    0.06
    \App
    0.06
    аб
    0.06
    ishop
    0.06
    isk
    0.06
    _DIFF
    0.06
     매우
    0.06
    ReuseIdentifier
    0.06
    (err
    0.06
    Act Density 0.062%

    No Known Activations