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

    Neuronpedia

    INDEX
    Explanations

    underwear

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of underwear or related undergarment terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    kle
    -0.07
    _socket
    -0.07
    損
    -0.07
     jes
    -0.07
     Phase
    -0.06
     Station
    -0.06
     projection
    -0.06
     cos
    -0.06
     sales
    -0.06
     jon
    -0.06
    POSITIVE LOGITS
     underwear
    0.10
     erect
    0.07
                    
↵
    0.07
    avir
    0.06
     dara
    0.06
    WithContext
    0.06
     ander
    0.06
     arose
    0.06
     arise
    0.06
    एक
    0.06
    Act Density 0.006%

    No Known Activations