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

    Neuronpedia

    INDEX
    Explanations

    references to unspecified or general entities, particularly people or things

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

    something someone things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sumpay
    -0.57
    DrawerToggle
    -0.55
    OGND
    -0.50
    WebElementEntity
    -0.49
     MainAxisSize
    -0.48
     echa
    -0.48
    awtextra
    -0.48
     deflation
    -0.46
     defaultstate
    -0.44
    kuwa
    -0.43
    POSITIVE LOGITS
     else
    0.53
     elsewhere
    0.47
     Them
    0.41
     sesuatu
    0.40
     everywhere
    0.40
     something
    0.39
     poprzed
    0.39
     THEM
    0.38
     coisa
    0.38
    THING
    0.38
    Act Density 0.030%

    No Known Activations