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

    Neuronpedia

    INDEX
    Explanations

    beginnings

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on date and year expressions, spotting temporal references in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nope
    -0.07
     resc
    -0.07
     forgiven
    -0.07
     SOUND
    -0.06
     обнаруж
    -0.06
    Ст
    -0.06
    ละคร
    -0.06
     बज
    -0.06
     усл
    -0.06
    ChangeListener
    -0.06
    POSITIVE LOGITS
     (!
    0.07
    档
    0.06
    igne
    0.06
     Sicher
    0.06
    -router
    0.06
     angular
    0.06
     ")[
    0.06
    #${
    0.06
                
    0.06
    #%%
    0.06
    Act Density 0.050%

    No Known Activations