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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash

    The neuron detects JavaScript strict‐mode directives (the "use strict" prologue) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Santo
    -0.06
    [
    -0.06
    BootApplication
    -0.06
     Patterson
    -0.06
     Cri
    -0.06
     collaborations
    -0.06
    Guard
    -0.06
    ディ
    -0.06
     afternoon
    -0.06
    니스
    -0.06
    POSITIVE LOGITS
    kre
    0.07
    aybe
    0.07
    -re
    0.07
     miesz
    0.06
    "struct
    0.06
    asmine
    0.06
     Maximum
    0.06
    ulf
    0.06
    png
    0.06
    ieving
    0.06
    Act Density 0.000%

    No Known Activations