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

    Neuronpedia

    INDEX
    Explanations

    terms related to change and transformation in various contexts

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

    alterations or modifications

    np_acts-logits-general · gemini-2.0-flash

    changing abstract concepts or situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setzen
    -0.51
     rijk
    -0.50
    {:
    -0.44
    zarchiwizowane
    -0.44
     novedades
    -0.43
     अच्छ
    -0.42
    devamını
    -0.42
     improvement
    -0.42
    ̍t
    -0.42
    擬
    -0.41
    POSITIVE LOGITS
     attitudes
    0.86
     perceptions
    0.85
     Zusammensetzung
    0.84
     paradigms
    0.82
     perception
    0.80
     fortunes
    0.79
     للاسماء
    0.78
     topology
    0.78
     wording
    0.78
     behaviour
    0.77
    Act Density 0.473%

    No Known Activations