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

    Neuronpedia

    INDEX
    Explanations

    cooking and baking

    np_max-act · gemini-2.0-flash

    The neuron detects descriptive quality words—adjectives and adverbs that characterize texture, appearance, or taste in cooking instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -offs
    -0.08
     textView
    -0.07
    птом
    -0.07
    ć
    -0.07
    Credentials
    -0.07
     вне
    -0.06
    Reader
    -0.06
    rane
    -0.06
     palate
    -0.06
     pancre
    -0.06
    POSITIVE LOGITS
    PRO
    0.07
     Reviewed
    0.06
     french
    0.06
    prs
    0.06
     migrants
    0.06
     CIT
    0.06
    RULE
    0.06
    ương
    0.06
     latina
    0.06
     SIX
    0.06
    Act Density 0.041%

    No Known Activations