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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the occurrence of the word “input.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lol
    -0.06
    Declared
    -0.06
    .lo
    -0.06
    ,image
    -0.06
    और
    -0.06
     adviser
    -0.06
    -review
    -0.06
     newer
    -0.06
     Paran
    -0.06
     Kerry
    -0.06
    POSITIVE LOGITS
    akukan
    0.07
     Breast
    0.07
    یشن
    0.07
    .setVertical
    0.06
    ection
    0.06
     недостат
    0.06
     snakes
    0.06
    आप
    0.06
    ()."
    0.06
    .Interval
    0.06
    Act Density 0.002%

    No Known Activations