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

    Neuronpedia

    INDEX
    Explanations

    elements related to recipes and cooking processes

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

    Followed by a form of "to be" or "to have."

    np_acts-logits-general · gemini-2.0-flash

    tastes and flavors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loob
    -0.54
    extAlignment
    -0.54
    WireFormatLite
    -0.54
    InteropServices
    -0.53
    Fluid
    -0.52
    serving
    -0.51
     FLUID
    -0.51
     Fluid
    -0.50
    ρών
    -0.50
     Haft
    -0.49
    POSITIVE LOGITS
     tastes
    1.26
     taste
    1.15
     tasted
    1.08
    taste
    0.93
     Taste
    0.86
     tasting
    0.82
    Taste
    0.81
     pair
    0.74
     pairs
    0.74
     schmeckt
    0.73
    Act Density 0.097%

    No Known Activations