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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens marking attribute or decorator syntax (e.g. the “@” in SwiftUI property wrappers, Angular @Input, HostListener, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     applicable
    -0.07
     LM
    -0.07
     Flint
    -0.07
    tah
    -0.07
     Cluster
    -0.07
     FD
    -0.07
     KD
    -0.07
     briefed
    -0.07
     Ud
    -0.07
    ussia
    -0.07
    POSITIVE LOGITS
     courageous
    0.07
    MarshalAs
    0.06
     обличчя
    0.06
    vably
    0.06
     jScrollPane
    0.06
     astonished
    0.06
     ');
    0.06
     strokeLine
    0.06
    のか
    0.06
    ?>><?
    0.06
    Act Density 0.003%

    No Known Activations