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

    Neuronpedia

    INDEX
    Explanations

    This neuron seems to activate on somewhat random words and phrases, perhaps short function words or verb phrases, and the content doesn't appear to create a coherent meaning.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mó
    -0.07
    moid
    -0.06
     slightly
    -0.06
    ãĤįãģĨ
    -0.06
    åħį
    -0.06
    invalid
    -0.06
     вполне
    -0.06
    irim
    -0.06
     Invalid
    -0.06
    æľī人
    -0.06
    POSITIVE LOGITS
     limited
    0.17
     lack
    0.17
     absence
    0.15
     lacking
    0.15
    limited
    0.14
     lacks
    0.14
    lack
    0.13
     minimal
    0.13
     lacked
    0.13
     Lack
    0.12
    Act Density 0.054%

    No Known Activations