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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “found in,” as used in “license that can be found in the LICENSE file.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    чен
    -0.07
     وهي
    -0.07
    rics
    -0.07
     Zu
    -0.06
     التو
    -0.06
    Benefits
    -0.06
     hä
    -0.06
    /native
    -0.06
     maka
    -0.06
     कब
    -0.06
    POSITIVE LOGITS
     ui
    0.06
    sim
    0.06
    (Pointer
    0.06
     dispatched
    0.06
    .ToolStrip
    0.06
    .Response
    0.06
    rm
    0.06
    	m
    0.06
     заход
    0.06
    -inter
    0.05
    Act Density 0.002%

    No Known Activations