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

    Neuronpedia

    INDEX
    Explanations

    File

    np_max-act · gemini-2.0-flash

    This neuron detects file‐header comments, specifically the “File:” labels in source‐file comment blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     영향을
    -0.07
    meaning
    -0.07
     ################################
    -0.07
    nop
    -0.06
     podmín
    -0.06
    ³
    -0.06
    .Pro
    -0.06
    sexo
    -0.06
    ajo
    -0.06
    ParticleSystem
    -0.06
    POSITIVE LOGITS
     TZ
    0.06
     trif
    0.06
    едак
    0.06
     QWidget
    0.06
    osit
    0.06
    /dis
    0.06
     enquiries
    0.06
     setSearch
    0.06
    лер
    0.06
    团
    0.06
    Act Density 0.006%

    No Known Activations