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

    Neuronpedia

    INDEX
    Explanations

    events

    np_max-act · gemini-2.0-flash

    This neuron detects statements reporting on complications or adverse events—especially negative declarations such as “no complications” or “did not occur.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ією
    -0.07
    .Results
    -0.06
    deadline
    -0.06
    بیر
    -0.06
    When
    -0.06
    compet
    -0.06
     出
    -0.06
    (et
    -0.06
     swimming
    -0.06
    .Preference
    -0.06
    POSITIVE LOGITS
     �
    0.07
     भव
    0.07
    <My
    0.06
     Faster
    0.06
     Maui
    0.06
     －
    0.06
     Соб
    0.06
    ','=
    0.06
    /pub
    0.06
     Kong
    0.06
    Act Density 0.020%

    No Known Activations