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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron detects Python code examples or explanations that use the os.listdir() function to list files in a directory.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Бер
    -0.07
     bại
    -0.07
     MetroFramework
    -0.07
    Ber
    -0.07
    elp
    -0.06
    translator
    -0.06
    об
    -0.06
    _ET
    -0.06
    /con
    -0.06
    _dd
    -0.06
    POSITIVE LOGITS
    Sigma
    0.06
    esor
    0.06
     Reads
    0.06
    inecraft
    0.06
    ›
    0.06
    (Bytes
    0.06
    Lambda
    0.06
    链接
    0.06
     phenotype
    0.06
     hack
    0.05
    Act Density 0.045%

    No Known Activations