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 identifies lines in source files that are part of large comment blocks describing copyright, license, or legal boilerplate.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     лист
    -0.07
     summary
    -0.07
    StringEncoding
    -0.07
    $category
    -0.07
     ceiling
    -0.07
     rotor
    -0.06
     BSP
    -0.06
     System
    -0.06
     fracture
    -0.06
     extrad
    -0.06
    POSITIVE LOGITS
     akşam
    0.07
    QM
    0.07
    Ctl
    0.06
    vla
    0.06
     Cisco
    0.06
     Williams
    0.06
    isan
    0.06
    BV
    0.06
    �
    0.06
    .rel
    0.06
    Act Density 0.007%

    No Known Activations