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

    Neuronpedia

    INDEX
    Explanations

    leadership positions

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of formal leadership titles (e.g. “king,” “monarch,” “President”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     poj
    -0.07
    mans
    -0.06
    なお
    -0.06
    IMP
    -0.06
    achers
    -0.06
    .mo
    -0.06
    idders
    -0.06
    awei
    -0.06
    .WindowManager
    -0.06
    、これ
    -0.06
    POSITIVE LOGITS
     Serge
    0.07
     "'",
    0.07
     Units
    0.07
    TECT
    0.06
     Cyan
    0.06
    erusform
    0.06
    ющ
    0.06
    Fant
    0.06
     ط
    0.06
    Vk
    0.06
    Act Density 0.032%

    No Known Activations