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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash

    This neuron fires on the Elixir “do” keyword (marking the start of a do‐block).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     голов
    -0.07
    ़े
    -0.06
     одне
    -0.06
     �
    -0.06
    oucí
    -0.06
    นน
    -0.06
     flagged
    -0.06
    -defined
    -0.06
    ufac
    -0.06
     landmark
    -0.06
    POSITIVE LOGITS
     couch
    0.07
     않고
    0.07
    вою
    0.06
    λύ
    0.06
     Kron
    0.06
     publi
    0.06
     předpok
    0.06
    ,true
    0.06
     fo
    0.06
     before
    0.06
    Act Density 0.000%

    No Known Activations