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

    Neuronpedia

    INDEX
    Explanations

    taking initiative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geschmack
    0.40
    Notation
    0.36
     вку
    0.36
     विटामिन
    0.35
    Napoleon
    0.35
    耘
    0.35
    心情
    0.34
    culas
    0.34
    ologisch
    0.34
     Displaystyle
    0.34
    POSITIVE LOGITS
    atives
    0.91
     initiative
    0.89
    itives
    0.83
    ATIVES
    0.83
     initiatives
    0.76
     iniciativa
    0.74
    ives
    0.70
     iniciativas
    0.64
    initiative
    0.64
    тивы
    0.60
    Act Density 0.005%

    No Known Activations