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

    Neuronpedia

    INDEX
    Explanations

    chemical

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “chemical” (especially in terms like “chemical industry,” “agrochemical,” or related product labels).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kuru
    -0.06
     /\
    -0.06
     جغراف
    -0.06
     Burr
    -0.06
     cave
    -0.06
     caves
    -0.06
     Reception
    -0.06
    비스
    -0.05
     centro
    -0.05
    <=(
    -0.05
    POSITIVE LOGITS
     LIFE
    0.07
     Ordinary
    0.06
     keeping
    0.06
    views
    0.06
    .views
    0.06
    -thinking
    0.06
    UM
    0.06
    serious
    0.06
     Tactics
    0.06
    ��
    0.06
    Act Density 0.008%

    No Known Activations