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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and their formatting in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical equations/formulas

    np_acts-logits-general · gemini-2.0-flash

    center aligned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.68
    oredCriteria
    -0.64
    provision
    -0.59
     provisioning
    -0.58
    ForRow
    -0.56
     पाल
    -0.53
     Provision
    -0.52
    PyExc
    -0.51
     Loaf
    -0.50
     Hogg
    -0.50
    POSITIVE LOGITS
     center
    1.23
    center
    1.15
     centre
    1.09
     centers
    1.03
     Center
    0.98
     CENTER
    0.98
    Center
    0.95
    CENTER
    0.94
     centering
    0.92
     centres
    0.90
    Act Density 0.072%

    No Known Activations