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

    Neuronpedia

    INDEX
    Explanations

    label

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of “label” in code or markup (e.g. form-field label attributes or documentation).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ulings
    -0.07
    group
    -0.07
     vests
    -0.07
    ikt
    -0.07
    .Visible
    -0.06
    -test
    -0.06
     conexion
    -0.06
     sorted
    -0.06
    Tracks
    -0.06
    Advice
    -0.06
    POSITIVE LOGITS
     remodeling
    0.06
    833
    0.06
    Launch
    0.06
     Lorenzo
    0.06
    777
    0.06
    Ι
    0.06
    AH
    0.06
    \ActiveForm
    0.06
     na
    0.06
    ؟
    0.06
    Act Density 0.010%

    No Known Activations