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

    Neuronpedia

    INDEX
    Explanations

    baking

    np_max-act · gemini-2.0-flash

    The neuron activates on cooking‐ or baking‐related language (i.e. mentions of baking and other cooking method terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    recipes for baking cakes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Grü
    -0.08
    holder
    -0.07
     Skype
    -0.07
    Occurs
    -0.06
    074
    -0.06
     Guerrero
    -0.06
     Gü
    -0.06
    .WinForms
    -0.06
     SGD
    -0.06
     WI
    -0.06
    POSITIVE LOGITS
     diesen
    0.06
     payday
    0.06
    рег
    0.06
    фіка
    0.06
     canada
    0.06
    -task
    0.06
    computer
    0.06
     medial
    0.06
     би
    0.06
     WideString
    0.06
    Act Density 0.001%

    No Known Activations