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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron is specialized to fire on the equality‐comparison operator “==” in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ิลป
    -0.07
     FormData
    -0.07
    urai
    -0.07
    atör
    -0.07
     áreas
    -0.06
    .decor
    -0.06
    Tabla
    -0.06
     mammals
    -0.06
    rikes
    -0.06
    arResult
    -0.06
    POSITIVE LOGITS
    ！↵
    0.07
    ůj
    0.07
    come
    0.06
     Riley
    0.06
     disproportion
    0.06
    Nu
    0.06
    �i
    0.06
     ``
    0.06
     공동
    0.06
     قر
    0.06
    Act Density 0.004%

    No Known Activations