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

    Neuronpedia

    INDEX
    Explanations

    ideology

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the root “ideolog-” (as in ideology, ideological, ideologies, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     taps
    -0.07
    (pin
    -0.06
    odafone
    -0.06
     incidence
    -0.06
     bins
    -0.06
     ajout
    -0.06
     куб
    -0.06
     deaths
    -0.06
     kitchen
    -0.06
     rover
    -0.06
    POSITIVE LOGITS
     ideology
    0.10
     ideological
    0.08
     Typed
    0.07
     defStyle
    0.07
    услов
    0.07
     polov
    0.07
     İl
    0.07
     χρη
    0.07
     Attend
    0.07
     getProperty
    0.07
    Act Density 0.005%

    No Known Activations