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

    Neuronpedia

    INDEX
    Explanations

    school, class

    np_max-act · gemini-2.0-flash

    This neuron detects when the text mentions an academic or school-assignment context (e.g. “school,” “project,” “course”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    HQ
    -0.07
     Blasio
    -0.06
    Number
    -0.06
     cg
    -0.06
     Charlie
    -0.06
    ско
    -0.06
    zoek
    -0.06
    Once
    -0.06
    _JOB
    -0.06
    _TWO
    -0.06
    POSITIVE LOGITS
     comrades
    0.07
    Τ
    0.07
     аж
    0.07
    izza
    0.06
     çeşit
    0.06
     이야
    0.06
    。不
    0.06
     ♥
    0.06
     pedestrian
    0.06
    ",__
    0.06
    Act Density 0.055%

    No Known Activations