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

    Neuronpedia

    INDEX
    Explanations

    Clearly, that

    np_max-act · gemini-2.0-flash

    This neuron detects discourse markers that signal something is obvious or apparent (e.g. “clearly,” “it will be appreciated,” “apparent”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lots
    -0.07
    .consume
    -0.07
     Screens
    -0.06
     Pepsi
    -0.06
    Operators
    -0.06
     watches
    -0.06
    adors
    -0.06
     bodies
    -0.06
     نگهداری
    -0.06
     Redirect
    -0.06
    POSITIVE LOGITS
    <iostream
    0.07
     explodes
    0.07
    )];↵
    0.06
    INCLUDE
    0.06
    rength
    0.06
    ']");↵
    0.06
    iever
    0.06
     estoy
    0.06
    设计器
    0.06
    olson
    0.06
    Act Density 0.014%

    No Known Activations