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

    Neuronpedia

    INDEX
    Explanations

    mentions of bees or bee-related terms

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

    Rambo or Kirby legal discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *)(
    -0.44
     Hodgson
    -0.43
    ]))
    -0.40
     CTP
    -0.40
     ninh
    -0.39
    ])[
    -0.39
    ])]
    -0.39
     NH
    -0.38
     ocul
    -0.38
     proven
    -0.37
    POSITIVE LOGITS
     Barbie
    2.30
    Barbie
    2.19
    barbie
    1.73
     barbie
    1.68
     Mattel
    1.05
     StatelessWidget
    0.71
     muñeca
    0.71
     boneca
    0.69
     ainfi
    0.66
     poupée
    0.65
    Act Density 0.001%

    No Known Activations