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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash

    This neuron identifies occurrences of the stem “clinic” (e.g. in words like “clinical” or “clinicopathological”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    äs
    -0.08
    send
    -0.07
    hands
    -0.07
     seaside
    -0.07
     Sand
    -0.07
     endowed
    -0.07
     صاح
    -0.07
     Hipp
    -0.06
    =P
    -0.06
    .Web
    -0.06
    POSITIVE LOGITS
     Clinic
    0.10
     clinics
    0.10
     clinic
    0.09
     quiz
    0.09
     Quiz
    0.08
    nici
    0.07
     Monitor
    0.07
     одну
    0.07
    ".
    0.07
     Bruno
    0.07
    Act Density 0.004%

    No Known Activations