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

    Neuronpedia

    INDEX
    Explanations

    create or time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emocional
    0.90
     simpt
    0.88
     torment
    0.82
     sorrow
    0.80
     heartbreaking
    0.79
     melancholy
    0.78
     migraine
    0.78
     sintomi
    0.77
     heartache
    0.77
     grie
    0.77
    POSITIVE LOGITS
    创建
    1.22
    创建一个
    1.11
     创建
    1.05
    create
    0.98
    CREATE
    0.95
     erstellen
    0.94
    Creating
    0.94
     Create
    0.92
    size
    0.92
    Create
    0.91
    Act Density 5.805%

    No Known Activations