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

    Neuronpedia

    INDEX
    Explanations

    joint

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “joint” (or “joints”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .bitmap
    -0.07
    ">$
    -0.06
     Burke
    -0.06
    ucle
    -0.06
     English
    -0.06
     Netflix
    -0.06
    Bitmap
    -0.06
    Buttons
    -0.06
     sizes
    -0.06
    Walk
    -0.06
    POSITIVE LOGITS
     joints
    0.12
     joint
    0.12
     Joint
    0.11
    joint
    0.10
    _joint
    0.10
    аст
    0.08
     合
    0.07
    Joint
    0.07
    oje
    0.07
     JOHN
    0.07
    Act Density 0.004%

    No Known Activations