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

    Neuronpedia

    INDEX
    Explanations

    ingredients and components used in formulations

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

    Ingredients or additives in products

    np_acts-logits-general · gemini-2.0-flash

    stabilizing ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tonode
    -0.58
     degust
    -0.54
     Audiodateien
    -0.54
    posedge
    -0.54
    Specificity
    -0.53
    fromnode
    -0.52
    Tembelea
    -0.52
    ''')
    -0.49
    parsedMessage
    -0.49
    ValueStyle
    -0.48
    POSITIVE LOGITS
     added
    0.68
     stabili
    0.66
     stabilis
    0.63
     stabil
    0.62
     stabilized
    0.61
    添加
    0.61
     ADDED
    0.60
    added
    0.59
     Added
    0.59
     stabilize
    0.59
    Act Density 0.489%

    No Known Activations