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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron preferentially activates on longer, multisyllabic nouns that denote internal states or positions of dependency (e.g. “anticipation,” “mercy,” or a placeholder name).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    UIScrollView
    -0.07
     display
    -0.06
    LOWER
    -0.06
     Several
    -0.06
    spl
    -0.06
    Bloc
    -0.06
    setOnClickListener
    -0.06
     mesaj
    -0.06
    optic
    -0.06
     енерг
    -0.06
    POSITIVE LOGITS
    _Task
    0.07
     terra
    0.06
    ử
    0.06
    (od
    0.06
    另
    0.06
     nắng
    0.06
     하지만
    0.06
     frankfurt
    0.06
     دیگر
    0.06
     medios
    0.06
    Act Density 0.059%

    No Known Activations