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

    Neuronpedia

    INDEX
    Explanations

    ankle

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect occurrences of the word “ankle.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dünyada
    -0.07
    Dict
    -0.07
     cult
    -0.07
     fld
    -0.07
    456
    -0.07
    Hits
    -0.07
    urovision
    -0.07
    出
    -0.07
     Dirt
    -0.07
    cccc
    -0.07
    POSITIVE LOGITS
     ankle
    0.13
     ankles
    0.10
     Ankara
    0.07
     Annie
    0.07
     knees
    0.07
    ानक
    0.07
    enny
    0.06
    -company
    0.06
     Anthem
    0.06
    _ENUM
    0.06
    Act Density 0.001%

    No Known Activations