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

    Neuronpedia

    INDEX
    Explanations

    approve

    np_max-act · gemini-2.0-flash

    The neuron detects calls‐to‐action around joining or registering (e.g. “join,” “register,” “request,” “approve”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    poke
    -0.07
     порт
    -0.07
     diy
    -0.07
    _tracker
    -0.06
    criptive
    -0.06
    NODE
    -0.06
    guided
    -0.06
    dni
    -0.06
     Supplier
    -0.06
    idue
    -0.06
    POSITIVE LOGITS
    	throw
    0.07
    	W
    0.07
    .Auto
    0.07
     عملیات
    0.07
     těla
    0.06
    \models
    0.06
    /part
    0.06
     이를
    0.06
    …ط
    0.06
     fieldValue
    0.06
    Act Density 0.029%

    No Known Activations