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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of reading or retrieving data from an external source.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tell
    -0.08
     CAP
    -0.07
    _strip
    -0.07
     علوم
    -0.07
     kettle
    -0.07
     тол
    -0.06
     구글상위
    -0.06
    술
    -0.06
    reports
    -0.06
    ween
    -0.06
    POSITIVE LOGITS
     polov
    0.07
    _der
    0.07
     automat
    0.06
    93
    0.06
    fake
    0.06
     머
    0.06
    _ml
    0.06
    .Yellow
    0.06
    Dual
    0.06
    _filtered
    0.06
    Act Density 0.023%

    No Known Activations