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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash

    The neuron is detecting the placeholder token “NAME_1” (i.e. an entity‐name placeholder).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     тобто
    -0.07
     yö
    -0.07
    _BR
    -0.06
     CZ
    -0.06
    .operation
    -0.06
    .LatLng
    -0.06
    Africa
    -0.06
     kale
    -0.06
    feld
    -0.06
    Ty
    -0.06
    POSITIVE LOGITS
    िजल
    0.07
    *:
    0.06
    uintptr
    0.06
     stark
    0.06
     процессе
    0.06
    孩
    0.06
     TWO
    0.06
    (master
    0.06
    .GetBytes
    0.06
    AxisAlignment
    0.06
    Act Density 0.004%

    No Known Activations