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

    Neuronpedia

    INDEX
    Explanations

    form new structures or define concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.77
     to
    0.70
    cı
    0.69
    لی
    0.66
    ப்
    0.61
    on
    0.61
    at
    0.61
     ngại
    0.61
    to
    0.60
    חר
    0.60
    POSITIVE LOGITS
    形成
    0.96
     गठन
    0.88
     गठित
    0.86
     formed
    0.81
     গঠিত
    0.80
     terbentuk
    0.78
     formación
    0.77
     formação
    0.77
     форми
    0.75
     formar
    0.70
    Act Density 0.048%

    No Known Activations