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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of law‐enforcement evidence collection (e.g. verbs like “seized,” “obtained,” “discovered” in the context of evidence).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ticks
    -0.07
    _GC
    -0.06
    LOOD
    -0.06
    ǎ
    -0.06
    QC
    -0.06
     Import
    -0.06
     mascara
    -0.06
     heater
    -0.06
     QC
    -0.06
     Validation
    -0.06
    POSITIVE LOGITS
     üretim
    0.07
     ),
↵
    0.07
    .ย
    0.07
    ObjectContext
    0.06
     вот
    0.06
    /WebAPI
    0.06
     crunchy
    0.06
     ".");↵
    0.06
     tho
    0.06
    필
    0.06
    Act Density 0.005%

    No Known Activations