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

    Neuronpedia

    INDEX
    Explanations

    invasion

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens, especially those representing dates or years.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Permission
    -0.07
    -property
    -0.06
    ustain
    -0.06
    пп
    -0.06
     job
    -0.06
    \Redirect
    -0.06
    Gar
    -0.06
    ats
    -0.06
    izarre
    -0.06
    ฺ
    -0.06
    POSITIVE LOGITS
     हमल
    0.07
     pacientes
    0.07
     lidi
    0.07
    )/(
    0.07
     smiles
    0.07
     эта
    0.06
    &page
    0.06
    žít
    0.06
    larım
    0.06
     gritty
    0.06
    Act Density 0.020%

    No Known Activations