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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs and verb phrases (especially infinitives) that describe the assistant’s purpose or intended function (e.g. “created to assist,” “designed to,” “help,” “provide”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    덕
    -0.07
    grunt
    -0.07
    Nej
    -0.06
    out
    -0.06
     работе
    -0.06
     Duc
    -0.06
     (("
    -0.06
     různých
    -0.06
    อให
    -0.06
    찰
    -0.06
    POSITIVE LOGITS
     tiểu
    0.08
    '*
    0.07
     �
    0.06
     floatValue
    0.06
    .OnItemClickListener
    0.06
    izzling
    0.06
     inclus
    0.06
     свер
    0.06
     newPath
    0.06
    <Location
    0.06
    Act Density 0.027%

    No Known Activations