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

    Neuronpedia

    INDEX
    Explanations

    Restraint

    np_max-act · gemini-2.0-flash

    This neuron detects descriptions of characters being physically restrained or bound (e.g., tied up, hands/feet cuffed or zip-tied).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    버
    -0.07
     covering
    -0.07
    puts
    -0.07
    .addCell
    -0.07
     VR
    -0.06
     nau
    -0.06
    oring
    -0.06
     peripherals
    -0.06
    第四
    -0.06
     stutter
    -0.06
    POSITIVE LOGITS
     detained
    0.08
     hindsight
    0.07
     İmparator
    0.06
    ISBN
    0.06
     Snowden
    0.06
    .tail
    0.06
    █
    0.06
     consequential
    0.06
     sidel
    0.06
    developer
    0.06
    Act Density 0.007%

    No Known Activations