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

    Neuronpedia

    INDEX
    Explanations

    Call to action

    np_max-act · gemini-2.0-flash

    The neuron primarily detects imperative or call-to-action verbs (commands and invitations to do something).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    's
    -0.07
    ’s
    -0.07
    DSL
    -0.07
     :＼
    -0.06
     roof
    -0.06
    eden
    -0.06
    itledBorder
    -0.06
     you
    -0.06
     reflux
    -0.06
     drainage
    -0.06
    POSITIVE LOGITS
     audition
    0.07
    WWW
    0.07
    ijo
    0.07
    (any
    0.07
    AMI
    0.07
     француз
    0.07
    imited
    0.06
     Guaranteed
    0.06
     ade
    0.06
     supplementary
    0.06
    Act Density 0.069%

    No Known Activations