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

    Neuronpedia

    INDEX
    Explanations

    references to vegetables in various contexts

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

    fruits and vegetables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ******/
    -0.47
     Rand
    -0.45
    annis
    -0.45
    nada
    -0.45
     Isaacs
    -0.44
    brief
    -0.43
    lost
    -0.43
     Martin
    -0.43
    parseLong
    -0.42
     Armand
    -0.42
    POSITIVE LOGITS
     vegetables
    1.75
     Vegetables
    1.59
    Vegetables
    1.53
    vegetables
    1.49
     veggies
    1.38
     légumes
    1.18
     овощи
    1.06
     verduras
    1.00
     verdura
    1.00
     sayuran
    0.95
    Act Density 0.005%

    No Known Activations