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

    Neuronpedia

    INDEX
    Explanations

    walk

    np_max-act · gemini-2.0-flash

    The neuron fires on Portuguese verb stems for physical activities—e.g. fragments of “caminhar,” “correr,” or “dançar.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    lam
    -0.06
     irrig
    -0.06
    лять
    -0.06
    .Callback
    -0.06
     swift
    -0.06
     prized
    -0.06
    ари
    -0.06
    ่
    -0.06
     Rift
    -0.06
     implicit
    -0.06
    POSITIVE LOGITS
    министра
    0.08
     gez
    0.07
     tinha
    0.07
    ασίας
    0.06
    Virginia
    0.06
    ’d
    0.06
     temperature
    0.06
    ORDER
    0.06
    abilecek
    0.06
    MORE
    0.06
    Act Density 0.007%

    No Known Activations