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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to weight or measurements

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

    Abbreviations related to time or measurement units

    np_acts-logits-general · gemini-2.0-flash

    units and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.61
    issau
    -0.58
     Baillargeon
    -0.55
    principalTable
    -0.53
     Waterhouse
    -0.51
    вік
    -0.49
    *~*~
    -0.49
     Ceinture
    -0.48
     Lazar
    -0.48
     TextAppearance
    -0.48
    POSITIVE LOGITS
    Eds
    1.04
     ops
    1.03
     Eds
    0.98
     Ops
    0.97
     mins
    0.97
    ubs
    0.95
     meds
    0.93
     cams
    0.93
     Docs
    0.92
    eds
    0.91
    Act Density 0.443%

    No Known Activations