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

    Neuronpedia

    INDEX
    Explanations

    Deer

    np_max-act · gemini-2.0-flash

    This neuron specifically detects occurrences of the word “deer.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -0.07
    /py
    -0.07
     Wire
    -0.07
    網
    -0.06
     فناوری
    -0.06
    _SM
    -0.06
    THON
    -0.06
     مصرف
    -0.06
    &S
    -0.06
    -holder
    -0.06
    POSITIVE LOGITS
     deer
    0.15
     Deer
    0.13
    deer
    0.09
     trout
    0.09
     '('
    0.08
     susceptible
    0.07
     Trout
    0.07
    鹿
    0.06
    divider
    0.06
     interchange
    0.06
    Act Density 0.006%

    No Known Activations