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

    Neuronpedia

    INDEX
    Explanations

    duct

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of inductors or inductance (terms containing “induct”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    apore
    -0.08
    .action
    -0.07
     Rape
    -0.07
     정부
    -0.06
    _BRANCH
    -0.06
    ظيف
    -0.06
    strncmp
    -0.06
     Extremely
    -0.06
    dashboard
    -0.06
    .serialization
    -0.06
    POSITIVE LOGITS
    iguous
    0.06
     Luke
    0.06
     ～
    0.06
     ddl
    0.06
    (Search
    0.06
     playlists
    0.06
     flora
    0.06
     Loan
    0.06
     Hardy
    0.06
     nichts
    0.06
    Act Density 0.003%

    No Known Activations