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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash

    The neuron flags Python file‐I/O calls—especially uses of open(…) and write(…) when saving to a file.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bio
    -0.07
    Wars
    -0.07
     director
    -0.07
    -going
    -0.06
    MemoryWarning
    -0.06
    -kit
    -0.06
     ji
    -0.06
     demand
    -0.06
    notEmpty
    -0.06
    访问
    -0.06
    POSITIVE LOGITS
     anv
    0.06
    юн
    0.06
     or
    0.06
     lw
    0.06
    dfa
    0.06
    _PL
    0.06
    _FC
    0.06
     intrig
    0.06
    ма
    0.06
     intrigued
    0.06
    Act Density 0.010%

    No Known Activations