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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on the legal phrase “leave to appeal,” i.e. requests for permission to appeal.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ImageView
    -0.07
    -tests
    -0.07
     viper
    -0.06
    enant
    -0.06
    	web
    -0.06
    ewitness
    -0.06
    .Matchers
    -0.06
    _NET
    -0.06
    <&
    -0.06
    Saturday
    -0.06
    POSITIVE LOGITS
    �
    0.06
     epic
    0.06
    งท
    0.06
    _IMPORTED
    0.06
    (Event
    0.06
    (callback
    0.06
    �
    0.06
    ADR
    0.06
     �
    0.06
    (xhr
    0.06
    Act Density 0.003%

    No Known Activations