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

    Neuronpedia

    INDEX
    Explanations

    hair tied back/up

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptions of hair being pulled back into a ponytail or similar up‐do.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    othy
    -0.06
    偷
    -0.06
    preci
    -0.06
     overl
    -0.06
     Sal
    -0.06
     aust
    -0.06
     intf
    -0.06
    ではない
    -0.06
     ******************************************************************************↵
    -0.06
     Ruth
    -0.06
    POSITIVE LOGITS
     vaping
    0.07
    Streaming
    0.07
     ارشد
    0.07
    _combine
    0.07
    Formatted
    0.07
    [],
    0.07
    StackNavigator
    0.07
    /plugin
    0.06
     farklı
    0.06
     ScrollView
    0.06
    Act Density 0.004%

    No Known Activations