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

    Neuronpedia

    INDEX
    Explanations

    references to food ingredients and cooking actions

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.50
     cornstarch
    -0.47
     propOrder
    -0.46
     blender
    -0.45
     tomato
    -0.45
    InjectAttribute
    -0.45
    __*/
    -0.45
     meringue
    -0.44
    DockStyle
    -0.44
     Blender
    -0.44
    POSITIVE LOGITS
     Soldaten
    0.40
     sencillo
    0.39
     Ganzen
    0.39
     acoged
    0.38
     alfombra
    0.37
     Tiefe
    0.36
     cáps
    0.36
     hırka
    0.36
     daraus
    0.36
     Einf
    0.35
    Act Density 0.023%

    No Known Activations