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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    This neuron fires on the imperative “let’s do this,” i.e. tokens expressing a group call‐to‐action.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .NonNull
    -0.07
     وج
    -0.07
     Lok
    -0.07
    (bitmap
    -0.06
     registrado
    -0.06
    獲
    -0.06
     smuggling
    -0.06
     Vaults
    -0.06
     GHz
    -0.06
     Paste
    -0.06
    POSITIVE LOGITS
    ivable
    0.07
    單
    0.06
    망
    0.06
     vriend
    0.06
    fair
    0.06
     타
    0.06
    adm
    0.06
     Madrid
    0.06
    dr
    0.06
    conditional
    0.06
    Act Density 0.007%

    No Known Activations