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

    Neuronpedia

    INDEX
    Explanations

    ist

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens ending in “ist,” i.e. the suffix marking professional or specialist titles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Freedom
    -0.07
     Innoc
    -0.07
     unre
    -0.06
     erro
    -0.06
    (peer
    -0.06
     "></
    -0.06
    ocoa
    -0.06
     WEB
    -0.06
     Kara
    -0.06
    re
    -0.06
    POSITIVE LOGITS
    ist
    0.14
    ists
    0.12
    IST
    0.12
     therapist
    0.09
     specialist
    0.09
    ologist
    0.09
    list
    0.09
    mist
    0.09
    rist
    0.09
    isz
    0.09
    Act Density 0.032%

    No Known Activations