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

    Neuronpedia

    INDEX
    Explanations

    brackets/parentheses

    np_max-act · gemini-2.0-flash

    This neuron fires on ORM model relationship definitions—especially ForeignKey and relationship/back_populates declarations linking tables.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -select
    -0.07
    DateString
    -0.07
    ochastic
    -0.07
    -за
    -0.06
     багато
    -0.06
    -process
    -0.06
     willingness
    -0.06
    REPORT
    -0.06
    市
    -0.06
    -INFRINGEMENT
    -0.06
    POSITIVE LOGITS
    ουσ
    0.07
     polov
    0.06
     Sz
    0.06
    ��
    0.06
     Netz
    0.06
    iddles
    0.06
     Assoc
    0.06
    ofilm
    0.06
     Ole
    0.06
     gif
    0.06
    Act Density 0.024%

    No Known Activations