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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the identifier “queue,” i.e. spots where a command or system queue object is referenced.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    udios
    -0.07
     bites
    -0.07
    führ
    -0.06
    Pid
    -0.06
     شکن
    -0.06
     raging
    -0.06
    urette
    -0.06
    ูช
    -0.06
    학과
    -0.06
     فرزند
    -0.06
    POSITIVE LOGITS
     Authorization
    0.07
    클
    0.07
     loung
    0.06
    <script
    0.06
                
↵
    0.06
    用
    0.06
     compromises
    0.06
     †
    0.06
     supplementary
    0.06
    )↵↵
    0.06
    Act Density 0.014%

    No Known Activations