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

    Neuronpedia

    INDEX
    Explanations

    handedness

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of handedness, especially when specifying left- or right-handed.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    สต
    -0.07
    .unregister
    -0.06
    Ter
    -0.06
     Selling
    -0.06
     Far
    -0.06
     Sok
    -0.06
     tally
    -0.06
     agreg
    -0.06
     awesome
    -0.06
    (sol
    -0.06
    POSITIVE LOGITS
     chủ
    0.06
    当
    0.06
    имв
    0.06
     bagi
    0.06
    beits
    0.06
    ................................
    0.06
    embed
    0.06
    			
↵			
↵
    0.06
    ................................
    0.06
     труда
    0.06
    Act Density 0.005%

    No Known Activations