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

    Neuronpedia

    INDEX
    Explanations

    directories

    np_max-act · gemini-2.0-flash

    shell scripts that involve file and directory operations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on tokens referring to directories or directory‐handling operations (e.g. “directory,” “subdirectories,” “opendir,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    697
    -0.07
     적
    -0.07
    ITE
    -0.06
     classics
    -0.06
    -it
    -0.06
    574
    -0.06
     kalk
    -0.06
     Deferred
    -0.06
    ogs
    -0.06
     Editors
    -0.06
    POSITIVE LOGITS
    .test
    0.07
    @Web
    0.07
    _Interface
    0.07
     sesame
    0.06
     سک
    0.06
     preg
    0.06
     selected
    0.06
    []);↵
    0.06
     getParent
    0.06
     سرم
    0.06
    Act Density 0.025%

    No Known Activations