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

    Neuronpedia

    INDEX
    Explanations

    Otherwise

    np_max-act · gemini-2.0-flash

    This neuron activates on the contrastive discourse marker “Otherwise.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     professionally
    -0.07
     bred
    -0.07
     clustered
    -0.06
     trà
    -0.06
    ò
    -0.06
     Negro
    -0.06
     Successful
    -0.06
    LED
    -0.06
    یل
    -0.06
     ship
    -0.06
    POSITIVE LOGITS
    mailbox
    0.07
     Otherwise
    0.07
     hues
    0.07
    _datos
    0.07
    .views
    0.07
     haha
    0.06
    MAND
    0.06
     �
    0.06
     ulož
    0.06
     QMessageBox
    0.06
    Act Density 0.006%

    No Known Activations