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

    Neuronpedia

    INDEX
    Explanations

    Improvement

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on floating‐point numeric values (decimal numbers) within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lith
    -0.06
     ball
    -0.06
    -0.06
     spectro
    -0.06
     timestep
    -0.06
    Mal
    -0.06
    (objects
    -0.06
    134
    -0.06
     blockchain
    -0.06
    -operation
    -0.06
    POSITIVE LOGITS
    .Dispose
    0.07
     waren
    0.06
    =$
    0.06
    /security
    0.06
    published
    0.06
    ivities
    0.06
    .level
    0.06
    /mysql
    0.06
     brit
    0.06
     brushes
    0.06
    Act Density 0.140%

    No Known Activations