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

    Neuronpedia

    INDEX
    Explanations

    forms of "to be"

    np_max-act · gemini-2.0-flash

    This neuron never activates on any tokens—it does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CJ
    -0.07
     JC
    -0.06
     coronary
    -0.06
    ostat
    -0.06
     LABEL
    -0.06
     entertaining
    -0.06
     LIABLE
    -0.06
    ,",
    -0.06
    _TD
    -0.06
     RG
    -0.06
    POSITIVE LOGITS
    delete
    0.08
    ajax
    0.06
     získ
    0.06
     recourse
    0.06
    ाइ
    0.06
     toned
    0.06
     craftsm
    0.06
     descricao
    0.06
    \Domain
    0.06
    SerializedName
    0.06
    Act Density 0.019%

    No Known Activations