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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron activates on cooking instruction verbs—especially mixing/stirring actions in recipes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    dater
    -0.07
    ffee
    -0.07
     záp
    -0.07
    Magic
    -0.07
    ,String
    -0.07
    (&(
    -0.06
     pope
    -0.06
    _Node
    -0.06
    ellers
    -0.06
     abused
    -0.06
    POSITIVE LOGITS
     NOI
    0.07
    ्रण
    0.06
    ほ
    0.06
     deactivated
    0.06
    ()):↵
    0.06
    .getAs
    0.06
    _selected
    0.06
     synonymous
    0.06
    	cin
    0.06
    .ToolStripButton
    0.06
    Act Density 0.005%

    No Known Activations