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

    Neuronpedia

    INDEX
    Explanations

    Code documentation

    np_max-act · gemini-2.0-flash

    The neuron activates on the substring “leigh,” as in “Rayleigh.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     McDon
    -0.06
     EX
    -0.06
     �
    -0.06
    .descriptor
    -0.06
     тв
    -0.06
     enslaved
    -0.06
    )”
    -0.06
     Ipsum
    -0.06
     Myanmar
    -0.06
     pamph
    -0.06
    POSITIVE LOGITS
     پژوهش
    0.07
     Αγ
    0.07
    continue
    0.07
    리가
    0.06
     countryside
    0.06
     juste
    0.06
    VOKE
    0.06
    leigh
    0.06
     Bre
    0.06
    (entry
    0.06
    Act Density 0.000%

    No Known Activations