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

    Neuronpedia

    INDEX
    Explanations

    Words ending in "ist"/"ism"

    np_max-act · gemini-2.0-flash

    This neuron specifically fires on the word “activist” (and its morphological variants like “activism,” “activists,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Choose
    -0.06
     showMessage
    -0.06
     envis
    -0.06
     MMP
    -0.06
    ้เป
    -0.06
    nowledge
    -0.06
     Mev
    -0.06
    interpret
    -0.06
     представляет
    -0.06
     MHz
    -0.06
    POSITIVE LOGITS
     activist
    0.10
     activists
    0.09
    ис
    0.07
     apl
    0.07
    sn
    0.07
     separat
    0.07
     awareness
    0.07
     activism
    0.07
    cl
    0.07
     资
    0.07
    Act Density 0.006%

    No Known Activations